Xiuying Chen

Shubo Tian, Qiao Jin, Lana Yeganova et al. · tsinghua

ChatGPT has drawn considerable attention from both the general public and domain experts with its remarkable text generation capabilities. This has subsequently led to the emergence of diverse applications in the field of biomedicine and health. In this work, we examine the diverse applications of large language models (LLMs), such as ChatGPT, in biomedicine and health. Specifically we explore the areas of biomedical information retrieval, question answering, medical text summarization, information extraction, and medical education, and investigate whether LLMs possess the transformative power to revolutionize these tasks or whether the distinct complexities of biomedical domain presents unique challenges. Following an extensive literature survey, we find that significant advances have been made in the field of text generation tasks, surpassing the previous state-of-the-art methods. For other applications, the advances have been modest. Overall, LLMs have not yet revolutionized biomedicine, but recent rapid progress indicates that such methods hold great potential to provide valuable means for accelerating discovery and improving health. We also find that the use of LLMs, like ChatGPT, in the fields of biomedicine and health entails various risks and challenges, including fabricated information in its generated responses, as well as legal and privacy concerns associated with sensitive patient data. We believe this survey can provide a comprehensive and timely overview to biomedical researchers and healthcare practitioners on the opportunities and challenges associated with using ChatGPT and other LLMs for transforming biomedicine and health.

Xiuying Chen, Hind Alamro, Mingzhe Li et al. · pku

The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers. Authors can save their time and effort by using the automatically generated related work section as a draft to complete the final related work. Most of the existing related work section generation methods rely on extracting off-the-shelf sentences to make a comparative discussion about the target work and the reference papers. However, such sentences need to be written in advance and are hard to obtain in practice. Hence, in this paper, we propose an abstractive target-aware related work generator (TAG), which can generate related work sections consisting of new sentences. Concretely, we first propose a target-aware graph encoder, which models the relationships between reference papers and the target paper with target-centered attention mechanisms. In the decoding process, we propose a hierarchical decoder that attends to the nodes of different levels in the graph with keyphrases as semantic indicators. Finally, to generate a more informative related work, we propose multi-level contrastive optimization objectives, which aim to maximize the mutual information between the generated related work with the references and minimize that with non-references. Extensive experiments on two public scholar datasets show that the proposed model brings substantial improvements over several strong baselines in terms of automatic and tailored human evaluations.

Mingzhe Li, XieXiong Lin, Xiuying Chen et al. · pku

Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the instance-level without discriminating the contribution of each word, while keywords are the gist of the text and dominant the constrained mapping relationships. Hence, in this work, we propose a hierarchical contrastive learning mechanism, which can unify hybrid granularities semantic meaning in the input text. Concretely, we first propose a keyword graph via contrastive correlations of positive-negative pairs to iteratively polish the keyword representations. Then, we construct intra-contrasts within instance-level and keyword-level, where we assume words are sampled nodes from a sentence distribution. Finally, to bridge the gap between independent contrast levels and tackle the common contrast vanishing problem, we propose an inter-contrast mechanism that measures the discrepancy between contrastive keyword nodes respectively to the instance distribution. Experiments demonstrate that our model outperforms competitive baselines on paraphrasing, dialogue generation, and storytelling tasks.

Juexiao Zhou, Xiuying Chen, Xin Gao

Medical artificial general intelligence (AGI) is an emerging field that aims to develop systems specifically designed for medical applications that possess the ability to understand, learn, and apply knowledge across a wide range of tasks and domains. Large language models (LLMs) represent a significant step towards AGI. However, training cross-domain LLMs in the medical field poses significant challenges primarily attributed to the requirement of collecting data from diverse domains. This task becomes particularly difficult due to privacy restrictions and the scarcity of publicly available medical datasets. Here, we propose Medical AGI (MedAGI), a paradigm to unify domain-specific medical LLMs with the lowest cost, and suggest a possible path to achieve medical AGI. With an increasing number of domain-specific professional multimodal LLMs in the medical field being developed, MedAGI is designed to automatically select appropriate medical models by analyzing users' questions with our novel adaptive expert selection algorithm. It offers a unified approach to existing LLMs in the medical field, eliminating the need for retraining regardless of the introduction of new models. This characteristic renders it a future-proof solution in the dynamically advancing medical domain. To showcase the resilience of MedAGI, we conducted an evaluation across three distinct medical domains: dermatology diagnosis, X-ray diagnosis, and analysis of pathology pictures. The results demonstrated that MedAGI exhibited remarkable versatility and scalability, delivering exceptional performance across diverse domains. Our code is publicly available to facilitate further research at https://github.com/JoshuaChou2018/MedAGI.

Xiuying Chen, Mingzhe Li, Shen Gao et al. · pku

Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline. Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order. To tackle this challenge, in this paper, we propose a Unified Timeline Summarizer (UTS) that can generate abstractive and extractive timeline summaries in time order. Concretely, in the encoder part, we propose a graph-based event encoder that relates multiple events according to their content dependency and learns a global representation of each event. In the decoder part, to ensure the chronological order of the abstractive summary, we propose to extract the feature of event-level attention in its generation process with sequential information remained and use it to simulate the evolutionary attention of the ground truth summary. The event-level attention can also be used to assist in extracting summary, where the extracted summary also comes in time sequence. We augment the previous Chinese large-scale timeline summarization dataset and collect a new English timeline dataset. Extensive experiments conducted on these datasets and on the out-of-domain Timeline 17 dataset show that UTS achieves state-of-the-art performance in terms of both automatic and human evaluations.

Xiuying Chen, Mingzhe Li, Xin Gao et al.

Despite the success achieved in neural abstractive summarization based on pre-trained language models, one unresolved issue is that the generated summaries are not always faithful to the input document. There are two possible causes of the unfaithfulness problem: (1) the summarization model fails to understand or capture the gist of the input text, and (2) the model over-relies on the language model to generate fluent but inadequate words. In this work, we propose a Faithfulness Enhanced Summarization model (FES), which is designed for addressing these two problems and improving faithfulness in abstractive summarization. For the first problem, we propose to use question-answering (QA) to examine whether the encoder fully grasps the input document and can answer the questions on the key information in the input. The QA attention on the proper input words can also be used to stipulate how the decoder should attend to the source. For the second problem, we introduce a max-margin loss defined on the difference between the language and the summarization model, aiming to prevent the overconfidence of the language model. Extensive experiments on two benchmark summarization datasets, CNN/DM and XSum, demonstrate that our model significantly outperforms strong baselines. The evaluation of factual consistency also shows that our model generates more faithful summaries than baselines.

Xiuying Chen, Guodong Long, Chongyang Tao et al.

A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models' robustness against perturbations including word-level synonym substitution and noise. To create semantic-consistent substitutes, we propose a SummAttacker, which is an efficient approach to generating adversarial samples based on language models. Experimental results show that state-of-the-art summarization models have a significant decrease in performance on adversarial and noisy test sets. Next, we analyze the vulnerability of the summarization systems and explore improving the robustness by data augmentation. Specifically, the first brittleness factor we found is the poor understanding of infrequent words in the input. Correspondingly, we feed the encoder with more diverse cases created by SummAttacker in the input space. The other factor is in the latent space, where the attacked inputs bring more variations to the hidden states. Hence, we construct adversarial decoder input and devise manifold softmixing operation in hidden space to introduce more diversity. Experimental results on Gigaword and CNN/DM datasets demonstrate that our approach achieves significant improvements over strong baselines and exhibits higher robustness on noisy, attacked, and clean datasets.

Xiuying Chen, Mingzhe Li, Shen Gao et al.

In a citation graph, adjacent paper nodes share related scientific terms and topics. The graph thus conveys unique structure information of document-level relatedness that can be utilized in the paper summarization task, for exploring beyond the intra-document information. In this work, we focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings. We first propose a Multi-granularity Unsupervised Summarization model (MUS) as a simple and low-cost solution to the task. MUS finetunes a pre-trained encoder model on the citation graph by link prediction tasks. Then, the abstract sentences are extracted from the corresponding paper considering multi-granularity information. Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework. Motivated by this, we next propose a Graph-based Supervised Summarization model (GSS) to achieve more accurate results on the task when large-scale labeled data are available. Apart from employing the link prediction as an auxiliary task, GSS introduces a gated sentence encoder and a graph information fusion module to take advantage of the graph information to polish the sentence representation. Experiments on a public benchmark dataset show that MUS and GSS bring substantial improvements over the prior state-of-the-art model.

Mingzhe Li, Xiuying Chen, Weiheng Liao et al.

Interview has been regarded as one of the most crucial step for recruitment. To fully prepare for the interview with the recruiters, job seekers usually practice with mock interviews between each other. However, such a mock interview with peers is generally far away from the real interview experience: the mock interviewers are not guaranteed to be professional and are not likely to behave like a real interviewer. Due to the rapid growth of online recruitment in recent years, recruiters tend to have online interviews, which makes it possible to collect real interview data from real interviewers. In this paper, we propose a novel application named EZInterviewer, which aims to learn from the online interview data and provides mock interview services to the job seekers. The task is challenging in two ways: (1) the interview data are now available but still of low-resource; (2) to generate meaningful and relevant interview dialogs requires thorough understanding of both resumes and job descriptions. To address the low-resource challenge, EZInterviewer is trained on a very small set of interview dialogs. The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource. Evaluation results on a real-world job interview dialog dataset indicate that we achieve promising results to generate mock interviews. With the help of EZInterviewer, we hope to make mock interview practice become easier for job seekers.

Xin Cheng, Shen Gao, Yuchi Zhang et al.

Review summarization is a non-trivial task that aims to summarize the main idea of the product review in the E-commerce website. Different from the document summary which only needs to focus on the main facts described in the document, review summarization should not only summarize the main aspects mentioned in the review but also reflect the personal style of the review author. Although existing review summarization methods have incorporated the historical reviews of both customer and product, they usually simply concatenate and indiscriminately model this two heterogeneous information into a long sequence. Moreover, the rating information can also provide a high-level abstraction of customer preference, it has not been used by the majority of methods. In this paper, we propose the Heterogeneous Historical Review aware Review Summarization Model (HHRRS) which separately models the two types of historical reviews with the rating information by a graph reasoning module with a contrastive loss. We employ a multi-task framework that conducts the review sentiment classification and summarization jointly. Extensive experiments on four benchmark datasets demonstrate the superiority of HHRRS on both tasks.

Xiuying Chen, Mingzhe Li, Jiayi Zhang et al.

As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the dialog generation task mostly augment all cases in the training dataset without considering the intrinsic attributes between different cases. We argue that not all cases are beneficial for augmentation task, and the cases suitable for augmentation should obey the following two attributes: (1) low-quality (the dialog model cannot generate a high-quality response for the case), (2) representative (the case should represent the property of the whole dataset). Herein, we explore this idea by proposing a Selective Data Augmentation framework (SDA) for the response generation task. SDA employs a dual adversarial network to select the lowest quality and most representative data points for augmentation in one stage. Extensive experiments conducted on two publicly available datasets, i.e., DailyDialog and OpenSubtitles, show that our framework can improve the response generation performance with respect to various metrics.

Taicheng Guo, Changsheng Ma, Xiuying Chen et al.

Reaction prediction, a critical task in synthetic chemistry, is to predict the outcome of a reaction based on given reactants. Generative models like Transformer have typically been employed to predict the reaction product. However, these likelihood-maximization models overlooked the inherent stochastic nature of chemical reactions, such as the multiple ways electrons can be redistributed among atoms during the reaction process. In scenarios where similar reactants could follow different electron redistribution patterns, these models typically predict the most common outcomes, neglecting less frequent but potentially crucial reaction patterns. These overlooked patterns, though rare, can lead to innovative methods for designing synthetic routes and significantly advance synthesis techniques. To address these limitations, we build a team of expert models to capture diverse plausible reaction outcomes for the same reactants, mimicking the divergent thinking of chemists. The proposed framework, ReactionTeam, is composed of specialized expert models, each trained to capture a distinct type of electron redistribution pattern in reaction, and a ranking expert that evaluates and orders the generated predictions. Experimental results across two widely used datasets and different data settings demonstrate that our proposed method achieves significantly better performance compared to existing state-of-the-art approaches.

Junfeng Liao, Qizhou Wang, Jianing Zhu et al.

LLM agents that operate over long context depend on external memory to accumulate knowledge over time. However, existing methods typically store each observation as a single deterministic conclusion (e.g., inferring "API~X failed" from temporary errors), even though such observations are inherently partial and potentially ambiguous. By committing to one conclusion and discarding uncertainty, these methods introduce self-reinforcing error: the agent acts on the stored conclusion, never revisits alternatives, and reinforces the conclusion over time. To address this issue, we propose BeliefMem, which shifts the memory paradigm from committing to a single conclusion per observation to retaining multiple candidate conclusions with their probabilities. Concretely, BeliefMem stores the candidate conclusions as separate memory entries, each carrying a probability that is updated via Noisy-OR rules as new observations arrive. At retrieval, all candidates surface together with their probabilities, keeping alternatives visible to the agent. Since each conclusion in memory retains its probability, BeliefMem preserves the uncertainty that the deterministic paradigm discards, enabling the agent to act with high confidence on well-evidenced knowledge while retaining the capacity to update its confidence when new evidence arrives. Empirical evaluations on LoCoMo and ALFWorld benchmarks show that, even with limited data, BeliefMem achieves the best average performance, remarkably outperforming well-known baselines. More broadly, such probabilistic memory produces substantial gains and explores a new direction for agent memory in partially observable environments.

Liuzhou Zhang, Zeyu Zhang, Biao Wu et al.

Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign.

Akash Ghosh, Tajamul Ashraf, Rishu Kumar Singh et al.

Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset.

Juexiao Zhou, Xiaonan He, Liyuan Sun et al.

Skin and subcutaneous diseases rank high among the leading contributors to the global burden of nonfatal diseases, impacting a considerable portion of the population. Nonetheless, the field of dermatology diagnosis faces three significant hurdles. Firstly, there is a shortage of dermatologists accessible to diagnose patients, particularly in rural regions. Secondly, accurately interpreting skin disease images poses a considerable challenge. Lastly, generating patient-friendly diagnostic reports is usually a time-consuming and labor-intensive task for dermatologists. To tackle these challenges, we present SkinGPT-4, which is the world's first interactive dermatology diagnostic system powered by an advanced visual large language model. SkinGPT-4 leverages a fine-tuned version of MiniGPT-4, trained on an extensive collection of skin disease images (comprising 52,929 publicly available and proprietary images) along with clinical concepts and doctors' notes. We designed a two-step training process to allow SkinGPT to express medical features in skin disease images with natural language and make accurate diagnoses of the types of skin diseases. With SkinGPT-4, users could upload their own skin photos for diagnosis, and the system could autonomously evaluate the images, identifies the characteristics and categories of the skin conditions, performs in-depth analysis, and provides interactive treatment recommendations. Meanwhile, SkinGPT-4's local deployment capability and commitment to user privacy also render it an appealing choice for patients in search of a dependable and precise diagnosis of their skin ailments. To demonstrate the robustness of SkinGPT-4, we conducted quantitative evaluations on 150 real-life cases, which were independently reviewed by certified dermatologists, and showed that SkinGPT-4 could provide accurate diagnoses of skin diseases.

Puning Yang, Junchi Yu, Qizhou Wang et al.

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and Distinguishable Refusal (DR), which steers models away from using sensitive knowledge during inference. Despite rapid progress, KD-based unlearning struggles with biased deletion due to suppressing specific token sequences as a substitute for complete knowledge removal, whereas DR-based unlearning risks the re-emergence of harmful knowledge because the underlying knowledge remains intact. To address these issues, we propose Distinguishable Deletion ($\mathrm{D^2}$), a paradigm that restricts the response distribution in the latent representation rather than specific tokens to erase undesirable knowledge, while distinguishing it from retained knowledge, enabling a refusal mechanism to handle unlearned inputs safely and coherently. To implement $\mathrm{D^2}$, we introduce an energy index that quantifies the presence of knowledge and the separation between unlearned and retained content. Mathematical and empirical analyses show that energy is both accurate and efficient, enabling Energy-based Unlearning Alignment (EUA) to enforce energy-boundary unlearning during training and apply an energy-based refusal mechanism at inference. Extensive experiments demonstrate that EUA significantly outperforms previous methods, indicating the superiority of $\mathrm{D^2}$. Our code is available at https://github.com/Puning97/EUA-for-LLM-Unlearning.

Yue Huang, Chujie Gao, Siyuan Wu et al.

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.

Juexiao Zhou, Bin Zhang, Xiuying Chen et al.

With the fast-growing and evolving omics data, the demand for streamlined and adaptable tools to handle the analysis continues to grow. In response to this need, we introduce Auto Bioinformatics Analysis (AutoBA), an autonomous AI agent based on a large language model designed explicitly for conventional omics data analysis. AutoBA simplifies the analytical process by requiring minimal user input while delivering detailed step-by-step plans for various bioinformatics tasks. Through rigorous validation by expert bioinformaticians, AutoBA's robustness and adaptability are affirmed across a diverse range of omics analysis cases, including whole genome sequencing (WGS), RNA sequencing (RNA-seq), single-cell RNA-seq, ChIP-seq, and spatial transcriptomics. AutoBA's unique capacity to self-design analysis processes based on input data variations further underscores its versatility. Compared with online bioinformatic services, AutoBA deploys the analysis locally, preserving data privacy. Moreover, different from the predefined pipeline, AutoBA has adaptability in sync with emerging bioinformatics tools. Overall, AutoBA represents a convenient tool, offering robustness and adaptability for complex omics data analysis.

Xiuying Chen, Tairan Wang, Taicheng Guo et al.

Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. Correspondingly, we introduce a QAMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data. We first address the issue of imbalanced label distribution by re-weighting the instance-wise loss based on the inverse frequency of each class, ensuring minority classes are not dominated by majority ones during optimization. Next, we utilize the unlabeled data to enrich the learning process, generating a variety of augmentations based on a SoftMix operation and ensuring their predictions align with the same target, i.e., pseudo-labels. To ensure the quality of the pseudo-labels, we propose a calibration procedure aimed at closely aligning the pseudo-label estimates of individual samples with a desired ground truth distribution. Experiments show that our QAMatch significantly outperforms the recent similar-scale baselines and Large Language Models (LLMs) not only on our ScholarChemQA dataset but also on four benchmark datasets. We hope our benchmark and model can facilitate and promote more research on chemical QA.

Lang Gao, Jinghui Zhang, Wei Liu et al.

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for the observed unpredictability of steering. By relaxing LRH's orthogonality assumption while preserving linear representations, we show that overlapping concept contributions naturally yield a sample-specific axis-orthogonal structure. We formalize this as the Cylindrical Representation Hypothesis (CRH). In CRH, a central axis captures the main difference between concept absence and presence and drives concept generation. A surrounding normal plane controls steering sensitivity by determining how easily the axis can activate the target concept. Within this plane, only specific sensitive sectors strongly facilitate concept activation, while other sectors can suppress or delay it. While the surrounding normal plane can be reliably identified from difference vectors, the sensitive sector cannot, introducing intrinsic uncertainty at the sector level. This uncertainty provides a principled explanation for why steering outcomes often fluctuate even when using well-aligned directions. Our experiments verify the existence of the cylindrical structure and demonstrate that CRH provides a valid and practical way to interpret model steering behavior in real settings: https://github.com/mbzuai-nlp/CRH.

Linfeng Du, Ye Yuan, Zichen Zhao et al.

Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alternative to fine-tuning by conditioning LLMs on user history records, and existing approaches typically select these records based on semantic relevance. We argue that relevance serves as an unreliable proxy for utility: a record may be semantically similar to a query yet fail to improve generation quality or even degrade it due to redundancy or conflicting information. To bridge this gap, we propose PURPLE, a contextual bandit framework that oPtimizes UseR Profiles for LLM pErsonalization. In contrast to a greedy selection of the most relevant records, PURPLE treats profile construction as an order-sensitive generation process and utilizes a Plackett-Luce ranking model to capture complex inter-record dependencies. By training with semantically rich feedback provided by the likelihood of the reference response, our method aligns retrieval directly with generation quality. Extensive experiments on nine personalization tasks demonstrate that PURPLE consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, establishing a principled and scalable solution for optimizing user profiles.

Zirui Song, Bin Yan, Yuhan Liu et al.

Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness in domain-specific applications that require specialized knowledge, such as healthcare, chemistry, or legal analysis. To address this, researchers have explored diverse methods to enhance LLMs by integrating domain-specific knowledge. In this survey, we provide a comprehensive overview of these methods, which we categorize into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization. Each approach offers unique mechanisms to equip LLMs with domain expertise, balancing trade-offs between flexibility, scalability, and efficiency. We discuss how these methods enable LLMs to tackle specialized tasks, compare their advantages and disadvantages, evaluate domain-specific LLMs against general LLMs, and highlight the challenges and opportunities in this emerging field. For those interested in delving deeper into this area, we also summarize the commonly used datasets and benchmarks. To keep researchers updated on the latest studies, we maintain an open-source at: https://github.com/abilliyb/Knowledge_Injection_Survey_Papers, dedicated to documenting research in the field of specialized LLM.

Qiang Yang, Xiuying Chen, Changsheng Ma et al.

The automatic classification of animal sounds presents an enduring challenge in bioacoustics, owing to the diverse statistical properties of sound signals, variations in recording equipment, and prevalent low Signal-to-Noise Ratio (SNR) conditions. Deep learning models like Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) have excelled in human speech recognition but have not been effectively tailored to the intricate nature of animal sounds, which exhibit substantial diversity even within the same domain. We propose an automated classification framework applicable to general animal sound classification. Our approach first optimizes audio features from Mel-frequency cepstral coefficients (MFCC) including feature rearrangement and feature reduction. It then uses the optimized features for the deep learning model, i.e., an attention-based Bidirectional LSTM (Bi-LSTM), to extract deep semantic features for sound classification. We also contribute an animal sound benchmark dataset encompassing oceanic animals and birds1. Extensive experimentation with real-world datasets demonstrates that our approach consistently outperforms baseline methods by over 25% in precision, recall, and accuracy, promising advancements in animal sound classification.

Fengxian Ji, Jingpu Yang, Zirui Song et al.

Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage, imprecise target-state definitions, and an overreliance on final-task success, obscuring where and why agents fail. To address this gap, we introduce \textbf{FineState-Bench}, a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state. FineState-Bench comprises 2,209 instances across desktop, web, and mobile platforms, spanning four interaction families and 23 UI component types, with each instance explicitly specifying an exact target state for fine-grained state setting. We further propose \textit{FineState-Metrics}, a four-stage diagnostic pipeline with stage-wise success rates: Localization Success Rate (SR@Loc), Interaction Success Rate (SR@Int), Exact State Success Rate at Locate (ES-SR@Loc), and Exact State Success Rate at Interact (ES-SR@Int), and a plug-and-play \textit{Visual Diagnostic Assistant} (VDA) that generates a Description and a bounding-box Localization Hint to diagnose visual grounding reason via controlled w/ vs.\ w/o comparisons. On FineState-Bench, exact goal-state success remains low: ES-SR@Int peaks at 32.8\% on Web and 22.8\% on average across platforms. With VDA localization hints, Gemini-2.5-Flash gains +14.9 ES-SR@Int points, suggesting substantial headroom from improved visual grounding, yet overall accuracy is still insufficient for reliable fine-grained state-conditioned interaction \href{https://github.com/FengxianJi/FineState-Bench}{Github.}

Chengrui Huang, Zhengliang Shi, Yuntao Wen et al.

Tool learning methods have enhanced the ability of large language models (LLMs) to interact with real-world applications. Many existing works fine-tune LLMs or design prompts to enable LLMs to select appropriate tools and correctly invoke them to meet user requirements. However, it is observed in previous works that the performance of tool learning varies from tasks, datasets, training settings, and algorithms. Without understanding the impact of these factors, it can lead to inconsistent results, inefficient model deployment, and suboptimal tool utilization, ultimately hindering the practical integration and scalability of LLMs in real-world scenarios. Therefore, in this paper, we explore the impact of both internal and external factors on the performance of tool learning frameworks. Through extensive experiments on two benchmark datasets, we find several insightful conclusions for future work, including the observation that LLMs can benefit significantly from increased trial and exploration. We believe our empirical study provides a new perspective for future tool learning research.

Fengxian Ji, Jingpu Yang, Zirui Song et al.

Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-world design projects remains uncertain. We introduce \textbf{ServImage}, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) \textbf{\textit{ServImageBench}}: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over \$295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations. (ii) \textbf{\textit{ServImageScore}}: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable. (iii) \textbf{\textit{ServImageModel}}: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00\% accuracy in predicting human payment decisions and producing calibrated payment probabilities. ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems \href{https://github.com/FengxianJi/ServImage}{Github.}

Mingxuan Cui, Jingpu Yang, Fengxian Ji et al.

Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through architecture-specific modules or encoder modifications, which complicate deployment across foundation models. We study text rendering as a post-training preference-alignment problem and propose TextAlign, a non-invasive framework that keeps the generator architecture unchanged. The key component is a hierarchical vision-language model (VLM)-based reward that decomposes rendering errors into global, word, and glyph levels, then converts binary defect judgments into a scalar preference signal. The resulting signal supports both Group Relative Policy Optimization (GRPO) and Direct Preference Optimization (DPO). Experiments on FLUX.1-dev and Z-Image-Turbo show consistent gains in OCR-based text accuracy without degrading general generation quality. Compared with strong foundation and text-rendering baselines, including SD3.5, Qwen-Image, AnyText, and TextDiffuser, these results indicate that reward design offers a scalable alternative to model redesign for improving text rendering.

Chenxi Wang, Zongfang Liu, Dequan Yang et al.

The impact of social media on critical issues such as echo chambers needs to be addressed, as these phenomena can have disruptive consequences for our society. Traditional research often oversimplifies emotional tendencies and opinion evolution into numbers and formulas, neglecting that news and communication are conveyed through text, which limits these approaches. Hence, in this work, we propose an LLM-based simulation for the social opinion network to evaluate and counter polarization phenomena. We first construct three typical network structures to simulate different characteristics of social interactions. Then, agents interact based on recommendation algorithms and update their strategies through reasoning and analysis. By comparing these interactions with the classic Bounded Confidence Model (BCM), the Friedkin Johnsen (FJ) model, and using echo chamber-related indices, we demonstrate the effectiveness of our framework in simulating opinion dynamics and reproducing phenomena such as opinion polarization and echo chambers. We propose two mitigation methods, active and passive nudges, that can help reduce echo chambers, specifically within language-based simulations. We hope our work will offer valuable insights and guidance for social polarization mitigation.

Kaiyang Wan, Honglin Mu, Rui Hao et al.

Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres to strict requirements in a single pass. This challenge is unsurprising, as successful human writing, according to the Cognitive Writing Theory, is a complex cognitive process involving iterative planning, translating, reviewing, and monitoring. Motivated by these cognitive principles, we aim to equip LLMs with human-like cognitive writing capabilities through CogWriter, a novel training-free framework that transforms LLM constrained long-form text generation into a systematic cognitive writing paradigm. Our framework consists of two key modules: (1) a Planning Agent that performs hierarchical planning to decompose the task, and (2) multiple Generation Agents that execute these plans in parallel. The system maintains quality via continuous monitoring and reviewing mechanisms, which evaluate outputs against specified requirements and trigger necessary revisions. CogWriter demonstrates exceptional performance on LongGenBench, a benchmark for complex constrained long-form text generation. Even when using Qwen-2.5-14B as its backbone, CogWriter surpasses GPT-4o by 22% in complex instruction completion accuracy while reliably generating texts exceeding 10,000 words. We hope this cognitive science-inspired approach provides a paradigm for LLM writing advancements: \href{https://github.com/KaiyangWan/CogWriter}{CogWriter}.

Xiaoqing Zhang, Ang Lv, Yuhan Liu et al.

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as ICL demonstrations increase from a few to many, performance tends to plateau and eventually decline. We identify two primary causes for this trend: the suboptimal negative log-likelihood (NLL) optimization objective and the incremental data noise. To address these issues, we introduce \textit{DrICL}, a novel optimization method that enhances model performance through \textit{Differentiated} and \textit{Reweighting} objectives. Globally, DrICL utilizes differentiated learning to optimize the NLL objective, ensuring that many-shot performance surpasses zero-shot levels. Locally, it dynamically adjusts the weighting of many-shot demonstrations by leveraging cumulative advantages inspired by reinforcement learning, thereby mitigating the impact of noisy data. Recognizing the lack of multi-task datasets with diverse many-shot distributions, we develop the \textit{Many-Shot ICL Benchmark} (ICL-50)-a large-scale benchmark of 50 tasks that cover shot numbers from 1 to 350 within sequences of up to 8,000 tokens-for both fine-tuning and evaluation purposes. Experimental results demonstrate that LLMs enhanced with DrICL achieve significant improvements in many-shot setups across various tasks, including both in-domain and out-of-domain scenarios. We release the code and dataset hoping to facilitate further research in many-shot ICL\footnote{https://github.com/xiaoqzhwhu/DrICL}.

Rui Zhao, Zeyu Zhang, Yi Xu et al.

Pedestrian detection in intelligent transportation systems has made significant progress but faces two critical challenges: (1) insufficient fusion of complementary information between visible and infrared spectra, particularly in complex scenarios, and (2) sensitivity to illumination changes, such as low-light or overexposed conditions, leading to degraded performance. To address these issues, we propose PedDet, an adaptive spectral optimization complementarity framework specifically enhanced and optimized for multispectral pedestrian detection. PedDet introduces the Multi-scale Spectral Feature Perception Module (MSFPM) to adaptively fuse visible and infrared features, enhancing robustness and flexibility in feature extraction. Additionally, the Illumination Robustness Feature Decoupling Module (IRFDM) improves detection stability under varying lighting by decoupling pedestrian and background features. We further design a contrastive alignment to enhance intermodal feature discrimination. Experiments on LLVIP and MSDS datasets demonstrate that PedDet achieves state-of-the-art performance, improving the mAP by 6.6% with superior detection accuracy even in low-light conditions, marking a significant step forward for road safety. Code will be available at https://github.com/AIGeeksGroup/PedDet.

Zixiang Xu, Yanbo Wang, Yue Huang et al.

Large language models (LLMs) are increasingly applied to socially grounded tasks, such as online community moderation, media content analysis, and social reasoning games. Success in these contexts depends on a model's social reasoning ability - the capacity to interpret social contexts, infer others' mental states, and assess the truthfulness of presented information. However, there is currently no systematic evaluation framework that comprehensively assesses the social reasoning capabilities of LLMs. Existing efforts often oversimplify real-world scenarios and consist of tasks that are too basic to challenge advanced models. To address this gap, we introduce SocialMaze, a new benchmark specifically designed to evaluate social reasoning. SocialMaze systematically incorporates three core challenges: deep reasoning, dynamic interaction, and information uncertainty. It provides six diverse tasks across three key settings: social reasoning games, daily-life interactions, and digital community platforms. Both automated and human validation are used to ensure data quality. Our evaluation reveals several key insights: models vary substantially in their ability to handle dynamic interactions and integrate temporally evolving information; models with strong chain-of-thought reasoning perform better on tasks requiring deeper inference beyond surface-level cues; and model reasoning degrades significantly under uncertainty. Furthermore, we show that targeted fine-tuning on curated reasoning examples can greatly improve model performance in complex social scenarios. The dataset is publicly available at: https://huggingface.co/datasets/MBZUAI/SocialMaze

Xiuying Chen, Tairan Wang, Juexiao Zhou et al.

Artificial intelligence (AI) systems, particularly those based on deep learning models, have increasingly achieved expert-level performance in medical applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations. The fairness issue has attracted considerable research interest in the medical imaging classification field, yet it remains understudied in the text generation domain. In this study, we investigate the fairness problem in text generation within the medical field and observe significant performance discrepancies across different races, sexes, and age groups, including intersectional groups, various model scales, and different evaluation metrics. To mitigate this fairness issue, we propose an algorithm that selectively optimizes those underperformed groups to reduce bias. The selection rules take into account not only word-level accuracy but also the pathology accuracy to the target reference, while ensuring that the entire process remains fully differentiable for effective model training. Our evaluations across multiple backbones, datasets, and modalities demonstrate that our proposed algorithm enhances fairness in text generation without compromising overall performance. Specifically, the disparities among various groups across different metrics were diminished by more than 30% with our algorithm, while the relative change in text generation accuracy was typically within 2%. By reducing the bias generated by deep learning models, our proposed approach can potentially alleviate concerns about the fairness and reliability of text generation diagnosis in medical domain. Our code is publicly available to facilitate further research at https://github.com/iriscxy/GenFair.

Yanbo Wang, Zixiang Xu, Yue Huang et al.

Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or retrieval-based distractions, such static methods show limited effectiveness against contemporary models. To address this problem, we propose a dynamic distraction generation framework based on tree search, where the generation process is guided by model behavior. Without modifying the original question or answer, the method efficiently produces challenging adaptive distractions across multiple datasets, enabling systematic stress testing of LLMs' contextual robustness. Experiments on four benchmarks demonstrate that the generated distractions lead to an average performance drop of over 45\% for mainstream models. Further comparisons of mitigation strategies show that prompt-based optimization methods yield limited gains, whereas post-training approaches (e.g., DPO) significantly enhance the model's contextual robustness. The results indicate that these issues do not stem from knowledge deficits in LLMs, but from a fundamental inability to maintain consistent reasoning under contextual distraction, posing a major challenge to the reliability of LLMs in real-world applications. The code is publicly available at https://github.com/wyf23187/Adaptive_Distractions.

Zixiang Xu, Yanbo Wang, Yue Huang et al.

Large Language Models (LLMs) have achieved remarkable success in Natural Language Processing (NLP), yet their cross-lingual performance consistency remains a significant challenge. This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in LLMs. Our approach leverages beam search and LLM-based simulation to generate bilingual question pairs that expose performance discrepancies between English and target languages. We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models. The extensive experiments demonstrate that our method precisely and cost-effectively pinpoints cross-lingual weaknesses, consistently revealing over 50\% accuracy drops in target languages across a wide range of models. Moreover, further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns and benefit from targeted post-training. Code is available at https://github.com/xzx34/Cross-Lingual-Pitfalls.

Akash Ghosh, Subhadip Baidya, Sriparna Saha et al.

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address this, we propose MedFocusLeak, a highly transferable black-box multimodal attack that induces incorrect yet clinically plausible diagnoses while keeping perturbations imperceptible. The method injects coordinated perturbations into non-diagnostic background regions and employs an attention distraction mechanism to shift the model's focus away from pathological areas. Extensive evaluations across six medical imaging modalities show that MedFocusLeak achieves state-of-the-art performance, generating misleading yet realistic diagnostic outputs across diverse VLMs. We further introduce a unified evaluation framework with novel metrics that jointly capture attack success and image fidelity, revealing a critical weakness in the reasoning capabilities of modern clinical VLMs.

Chong Tian, Yu Wang, Chenxu Yang et al.

Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationships are subtly inconsistent, like mismatched visuals and captions. On two benchmark datasets, FakeSV (Chinese) and FakeTT (English), we observe a clear asymmetry: real videos exhibit high text-visual but moderate text-audio consistency, while fake videos show the opposite pattern. Moreover, a single global consistency score forms an interpretable axis along which fake probability and prediction errors vary smoothly. Motivated by these observations, we present MAGIC3 (Modal-Adversarial Gated Interaction and Consistency-Centric Classifier), a detector that explicitly models and exposes cross-tri-modal consistency signals at multiple granularities. MAGIC3 combines explicit pairwise and global consistency modeling with token- and frame-level consistency signals derived from cross-modal attention, incorporates multi-style LLM rewrites to obtain style-robust text representations, and employs an uncertainty-aware classifier for selective VLM routing. Using pre-extracted features, MAGIC3 consistently outperforms the strongest non-VLM baselines on FakeSV and FakeTT. While matching VLM-level accuracy, the two-stage system achieves 18-27x higher throughput and 93% VRAM savings, offering a strong cost-performance tradeoff.

Kaiyang Wan, Lang Gao, Honglin Mu et al.

Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise. This task is challenging for LLMs as they have a finite per-pass output capacity, beyond which the integration of task-relevant evidence proves unreliable. Consequently, the single-pass reasoning paradigm is inherently vulnerable to this capacity overflow. To formalize this bottleneck, our analysis establishes a Fano-style accuracy upper bound, defining a theoretical performance ceiling for single-pass LLMs. This bound reveals that accuracy inevitably collapses once task complexity exceeds model capacity, providing general principles for capacity-aware representation and structuring of MHQA in LLMs. Building on these principles, we introduce a proof-of-concept multi-call framework for MHQA, InfoQA. It ensures high per-step accuracy by combining capacity-aware task decomposition with active pruning of prior reasoning traces, keeping the information load within the single-pass limit. It further achieves robustness by a dependency-explicit workflow that enables precise control over the reasoning path. We construct a stringent and noise-rich benchmark to validate our theory and framework. Experimental results show that model behavior aligns with our predicted capacity curves while InfoQA achieves consistent performance improvements. We hope our work inspires more LLM multi-step reasoning methods: \faGithub \href{https://github.com/KaiyangWan/InfoQA}{InfoQA}.

Tianle Gu, Zongqi Wang, Kexin Huang et al.

Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. However, it fails in low-entropy scenarios, where predictable outputs make green token selection difficult without disrupting natural text flow. Existing approaches address this by assuming access to the original LLM to calculate entropy and selectively watermark high-entropy tokens. However, these methods face two major challenges: (1) high computational costs and detection delays due to reliance on the original LLM, and (2) potential risks of model leakage. To address these limitations, we propose Invisible Entropy (IE), a watermarking paradigm designed to enhance both safety and efficiency. Instead of relying on the original LLM, IE introduces a lightweight feature extractor and an entropy tagger to predict whether the entropy of the next token is high or low. Furthermore, based on theoretical analysis, we develop a threshold navigator that adaptively sets entropy thresholds. It identifies a threshold where the watermark ratio decreases as the green token count increases, enhancing the naturalness of the watermarked text and improving detection robustness. Experiments on HumanEval and MBPP datasets demonstrate that IE reduces parameter size by 99\% while achieving performance on par with state-of-the-art methods. Our work introduces a safe and efficient paradigm for low-entropy watermarking. https://github.com/Carol-gutianle/IE https://huggingface.co/datasets/Carol0110/IE-Tagger

Honglin Mu, Jinghao Liu, Kaiyang Wan et al.

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task. Notably, while defenses may exist for mature domains such as code review, they are often absent in other common applications such as resume screening and peer review. This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types. We evaluate two defense mechanisms: prompt-based defenses achieve 10.1% attack reduction with 12.5% false rejection increase, while our proposed FIDS (Foreign Instruction Detection through Separation) using LoRA adaptation achieves 15.4% attack reduction with 10.4% false rejection increase. The combined approach provides 26.3% attack reduction, demonstrating that training-time defenses outperform inference-time mitigations in both security and utility preservation.

Qiang Yang, Xiuying Chen, Changsheng Ma et al.

The global impact of the COVID-19 pandemic has highlighted the need for a comprehensive understanding of public sentiment and reactions. Despite the availability of numerous public datasets on COVID-19, some reaching volumes of up to 100 billion data points, challenges persist regarding the availability of labeled data and the presence of coarse-grained or inappropriate sentiment labels. In this paper, we introduce SenWave, a novel fine-grained multi-language sentiment analysis dataset specifically designed for analyzing COVID-19 tweets, featuring ten sentiment categories across five languages. The dataset comprises 10,000 annotated tweets each in English and Arabic, along with 30,000 translated tweets in Spanish, French, and Italian, derived from English tweets. Additionally, it includes over 105 million unlabeled tweets collected during various COVID-19 waves. To enable accurate fine-grained sentiment classification, we fine-tuned pre-trained transformer-based language models using the labeled tweets. Our study provides an in-depth analysis of the evolving emotional landscape across languages, countries, and topics, revealing significant insights over time. Furthermore, we assess the compatibility of our dataset with ChatGPT, demonstrating its robustness and versatility in various applications. Our dataset and accompanying code are publicly accessible on the repository\footnote{https://github.com/gitdevqiang/SenWave}. We anticipate that this work will foster further exploration into fine-grained sentiment analysis for complex events within the NLP community, promoting more nuanced understanding and research innovations.

Yanbo Wang, Zixiang Xu, Yue Huang et al.

Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed processes, which limits their adaptability across different tasks. While a few methods attempt automated workflow generation, they are often tied to specific datasets or query types and make limited use of intermediate feedback, reducing system robustness and reasoning depth. Moreover, their operations are typically predefined and inflexible. To address these limitations, we propose DyFlow, a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback, thereby enhancing cross-task generalization. DyFlow consists of two core components: a designer and an executor. The designer decomposes complex problems into a sequence of sub-goals defined by high-level objectives and dynamically plans the next steps based on intermediate outputs and feedback. These plans are then carried out by the executor, which executes each operation using dynamic operators with context-aware parameterization, enabling flexible and semantically grounded reasoning. We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation. Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains. The code is publicly available at https://github.com/wyf23187/DyFlow.

Fengxian Ji, Jingpu Yang, Zirui Song et al.

With the rapid advancement of generative artificial intelligence technology, Graphical User Interface (GUI) agents have demonstrated tremendous potential for autonomously managing daily tasks through natural language instructions. However, current evaluation frameworks for GUI agents suffer from fundamental flaws: existing benchmarks overly focus on coarse-grained task completion while neglecting fine-grained control capabilities crucial for real-world applications. To address this, we introduce FineState-Bench, the first evaluation and diagnostic standard for fine-grained GUI proxy operations, designed to quantify fine-grained control. This multi-platform (desktop, Web, mobile) framework includes 2257 task benchmarks in four components and uses a four-phase indicator for comprehensive perception-to-control assessment. To analyze perception and positioning for refined operations, we developed the plug-and-play Visual Diagnostic Assistant (VDA), enabling the first quantitative decoupling analysis of these capabilities. Experimental results on our benchmark show that the most advanced models achieve only 32.8% fine-grained interaction accuracy. Using our VDA in controlled experiments, quantifying the impact of visual capabilities, we showed that ideal visual localization boosts Gemini-2.5-Flash's success rate by 14.9\%. Our diagnostic framework confirms for the first time that the primary bottleneck for current GUI proxies is basic visual positioning capability.All resources are fully open-source. github: https://github.com/AnonymousThewarehouse/FineState-Bench huggingface: https://huggingface.co/datasets/Willtime2006/Static-FineBench

Ruixiang Feng, Shen Gao, Xiuying Chen et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural biases, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality, but also risks reinforcing stereotypes and perpetuating discrimination. To address this, we propose CulFiT, a novel culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. Our approach synthesizes diverse cultural-related questions, constructs critique data in culturally relevant languages, and employs fine-grained rewards to decompose cultural texts into verifiable knowledge units for interpretable evaluation. We also introduce GlobalCultureQA, a multilingual open-ended question-answering dataset designed to evaluate culturally-aware responses in a global context. Extensive experiments on three existing benchmarks and our GlobalCultureQA demonstrate that CulFiT achieves state-of-the-art open-source model performance in cultural alignment and general reasoning.

Xiuying Chen, Mingzhe Li, Shen Gao et al.

A proficient summarization model should exhibit both flexibility -- the capacity to handle a range of in-domain summarization tasks, and adaptability -- the competence to acquire new knowledge and adjust to unseen out-of-domain tasks. Unlike large language models (LLMs) that achieve this through parameter scaling, we propose a more parameter-efficient approach in this study. Our motivation rests on the principle that the general summarization ability to capture salient information can be shared across different tasks, while the domain-specific summarization abilities need to be distinct and tailored. Concretely, we propose MoeSumm, a Mixture-of-Expert Summarization architecture, which utilizes a main expert for gaining the general summarization capability and deputy experts that selectively collaborate to meet specific summarization task requirements. We further propose a max-margin loss to stimulate the separation of these abilities. Our model's distinct separation of general and domain-specific summarization abilities grants it with notable flexibility and adaptability, all while maintaining parameter efficiency. MoeSumm achieves flexibility by managing summarization across multiple domains with a single model, utilizing a shared main expert and selected deputy experts. It exhibits adaptability by tailoring deputy experts to cater to out-of-domain few-shot and zero-shot scenarios. Experimental results on 11 datasets show the superiority of our model compared with recent baselines and LLMs. We also provide statistical and visual evidence of the distinct separation of the two abilities in MoeSumm (https://github.com/iriscxy/MoE_Summ).

Taicheng Guo, Xiuying Chen, Yaqi Wang et al.

Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.

Jiabao Fang, Shen Gao, Pengjie Ren et al.

Due to strong capabilities in conducting fluent, multi-turn conversations with users, Large Language Models (LLMs) have the potential to further improve the performance of Conversational Recommender System (CRS). Unlike the aimless chit-chat that LLM excels at, CRS has a clear target. So it is imperative to control the dialogue flow in the LLM to successfully recommend appropriate items to the users. Furthermore, user feedback in CRS can assist the system in better modeling user preferences, which has been ignored by existing studies. However, simply prompting LLM to conduct conversational recommendation cannot address the above two key challenges. In this paper, we propose Multi-Agent Conversational Recommender System (MACRS) which contains two essential modules. First, we design a multi-agent act planning framework, which can control the dialogue flow based on four LLM-based agents. This cooperative multi-agent framework will generate various candidate responses based on different dialogue acts and then choose the most appropriate response as the system response, which can help MACRS plan suitable dialogue acts. Second, we propose a user feedback-aware reflection mechanism which leverages user feedback to reason errors made in previous turns to adjust the dialogue act planning, and higher-level user information from implicit semantics. We conduct extensive experiments based on user simulator to demonstrate the effectiveness of MACRS in recommendation and user preferences collection. Experimental results illustrate that MACRS demonstrates an improvement in user interaction experience compared to directly using LLMs.

Zhangming Chan, Xiuying Chen, Yongliang Wang et al.

Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information. However, little attention has been paid to this problem. To bridge this gap, we propose a model named Fidelity-oriented Product Description Generator (FPDG). FPDG takes the entity label of each word into account, since the product attribute information is always conveyed by entity words. Specifically, we first propose a Recurrent Neural Network (RNN) decoder based on the Entity-label-guided Long Short-Term Memory (ELSTM) cell, taking both the embedding and the entity label of each word as input. Second, we establish a keyword memory that stores the entity labels as keys and keywords as values, allowing FPDG to attend to keywords by attending to their entity labels. Experiments conducted on a large-scale real-world product description dataset show that our model achieves state-of-the-art performance in terms of both traditional generation metrics and human evaluations. Specifically, FPDG increases the fidelity of the generated descriptions by 25%.

Han Bao, Yue Huang, Yanbo Wang et al.

Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information. However, the evaluation of LVLMs presents significant challenges as the evaluation benchmark always demands lots of human cost for its construction, and remains static, lacking flexibility once constructed. Even though automatic evaluation has been explored in textual modality, the visual modality remains under-explored. As a result, in this work, we address a question: "Can LVLMs themselves be used to benchmark each other in the visual automatically domain?". We introduce AutoBench-V, an automated framework for serving evaluation on demand, i.e., benchmarking LVLMs based on specific aspects of model capability. AutoBench-V leverages text-to-image models to generate relevant image samples and then utilizes LVLMs to orchestrate visual question-answering (VQA) tasks, completing the evaluation process efficiently and flexibly. Through an extensive evaluation of nine popular LVLMs across five demanded user inputs (i.e., evaluation capabilities), the framework shows effectiveness and reliability.