Haiyun Jiang

Longyue Wang, Zefeng Du, Donghuai Liu et al.

Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of inter-sentence properties and overlook critical discourse phenomena that cross sentences. To bridge the gap, we propose Disco-Bench, a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks, covering understanding, translation, and generation. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena (e.g. cohesion and coherence) in Chinese and/or English. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge. We totally evaluate 20 general-, in-domain and commercial models based on Transformer, advanced pretraining architectures and large language models (LLMs). Our results show (1) the challenge and necessity of our evaluation benchmark; (2) fine-grained pretraining based on literary document-level training data consistently improves the modeling of discourse information. We will release the datasets, pretrained models, and leaderboard, which we hope can significantly facilitate research in this field: https://github.com/longyuewangdcu/Disco-Bench.

Yi Chen, Rui Wang, Haiyun Jiang et al.

Evaluating the quality of generated text is a challenging task in NLP, due to the inherent complexity and diversity of text. Recently, large language models (LLMs) have garnered significant attention due to their impressive performance in various tasks. Therefore, we present this paper to investigate the effectiveness of LLMs, especially ChatGPT, and explore ways to optimize their use in assessing text quality. We compared three kinds of reference-free evaluation methods. The experimental results prove that ChatGPT is capable of evaluating text quality effectively from various perspectives without reference and demonstrates superior performance than most existing automatic metrics. In particular, the Explicit Score, which utilizes ChatGPT to generate a numeric score measuring text quality, is the most effective and reliable method among the three exploited approaches. However, directly comparing the quality of two texts may lead to suboptimal results. We believe this paper will provide valuable insights for evaluating text quality with LLMs and have released the used data.

Yuhan Li, Peisong Wang, Xiao Zhu et al.

The emergence of large language models (LLMs) has revolutionized the way we interact with graphs, leading to a new paradigm called GraphLLM. Despite the rapid development of GraphLLM methods in recent years, the progress and understanding of this field remain unclear due to the lack of a benchmark with consistent experimental protocols. To bridge this gap, we introduce GLBench, the first comprehensive benchmark for evaluating GraphLLM methods in both supervised and zero-shot scenarios. GLBench provides a fair and thorough evaluation of different categories of GraphLLM methods, along with traditional baselines such as graph neural networks. Through extensive experiments on a collection of real-world datasets with consistent data processing and splitting strategies, we have uncovered several key findings. Firstly, GraphLLM methods outperform traditional baselines in supervised settings, with LLM-as-enhancers showing the most robust performance. However, using LLMs as predictors is less effective and often leads to uncontrollable output issues. We also notice that no clear scaling laws exist for current GraphLLM methods. In addition, both structures and semantics are crucial for effective zero-shot transfer, and our proposed simple baseline can even outperform several models tailored for zero-shot scenarios. The data and code of the benchmark can be found at https://github.com/NineAbyss/GLBench.

Mingyang Song, Haiyun Jiang, Shuming Shi et al.

The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.

Yongrui Chen, Haiyun Jiang, Xinting Huang et al.

The improvement of LLMs' instruction-following capabilities relies heavily on the availability of high-quality instruction-response pairs. Unfortunately, the current methods used to collect the pairs suffer from either unaffordable labor costs or severe hallucinations in the self-generation of LLM. To tackle these challenges, this paper proposes a scalable solution. It involves training LLMs to generate instruction-response pairs based on human-written documents, rather than relying solely on self-generation without context. Our proposed method not only exploits the advantages of human-written documents in reducing hallucinations but also utilizes an LLM to wrap the expression of documents, which enables us to bridge the gap between various document styles and the standard AI response. Experiments demonstrate that our method outperforms existing typical methods on multiple benchmarks. In particular, compared to the best-performing baseline, the LLM trained using our generated dataset exhibits a 10\% relative improvement in performance on AlpacaEval, despite utilizing only 1/5 of its training data. Furthermore, a comprehensive manual evaluation validates the quality of the data we generated. Our trained wrapper is publicly available at https://github.com/Bahuia/Dog-Instruct.

Jingping Liu, Yuqiu Song, Kui Xue et al.

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate multi-head self-attention and feed-forward network computation, making model optimization not very smooth. Hence, we propose a novel tuning way called layer tuning, aiming to add learnable parameters in Transformer layers. Specifically, we focus on layer tuning for feed-forward network in the Transformer, namely FL-tuning. It introduces additional units into the hidden layer of each feed-forward network. We conduct extensive experiments on the public CLUE benchmark. The results show that: 1) Our FL-tuning outperforms prompt tuning methods under both full-data and few-shot settings in almost all cases. In particular, it improves accuracy by 17.93% (full-data setting) on WSC 1.0 and F1 by 16.142% (few-shot setting) on CLUENER over P-tuning v2. 2) Our FL-tuning is more stable and converges about 1.17 times faster than P-tuning v2. 3) With only about 3% of Transformer's parameters to be trained, FL-tuning is comparable with fine-tuning on most datasets, and significantly outperforms fine-tuning (e.g., accuracy improved by 12.9% on WSC 1.1) on several datasets. The source codes are available at https://github.com/genggui001/FL-Tuning.

Nuo Chen, Yan Wang, Haiyun Jiang et al.

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series and is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes. These extensive annotations may empower LLMs to unlock character-driven dialogue capabilities. Furthermore, it can serve as a universal benchmark for evaluating how well can a LLM aligning with a specific character. We benchmark LLMs on HPD using both fine-tuning and in-context learning settings. Evaluation results reveal that although there is substantial room for improvement in generating high-quality, character-aligned responses, the proposed dataset is valuable in guiding models toward responses that better align with the character of Harry Potter.

Hongzhan Lin, Pengyao Yi, Jing Ma et al.

The spread of rumors along with breaking events seriously hinders the truth in the era of social media. Previous studies reveal that due to the lack of annotated resources, rumors presented in minority languages are hard to be detected. Furthermore, the unforeseen breaking events not involved in yesterday's news exacerbate the scarcity of data resources. In this work, we propose a novel zero-shot framework based on prompt learning to detect rumors falling in different domains or presented in different languages. More specifically, we firstly represent rumor circulated on social media as diverse propagation threads, then design a hierarchical prompt encoding mechanism to learn language-agnostic contextual representations for both prompts and rumor data. To further enhance domain adaptation, we model the domain-invariant structural features from the propagation threads, to incorporate structural position representations of influential community response. In addition, a new virtual response augmentation method is used to improve model training. Extensive experiments conducted on three real-world datasets demonstrate that our proposed model achieves much better performance than state-of-the-art methods and exhibits a superior capacity for detecting rumors at early stages.

Shuming Shi, Enbo Zhao, Duyu Tang et al.

In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently by using artificial intelligence (AI) technologies. Previous writing assistants typically provide the function of error checking (to detect and correct spelling and grammatical errors) and limited text-rewriting functionality. With the emergence of large-scale neural language models, some systems support automatically completing a sentence or a paragraph. In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME). In the text completion category, Effidit supports generation-based sentence completion, retrieval-based sentence completion, and phrase completion. In contrast, many other writing assistants so far only provide one or two of the three functions. For text polishing, we have three functions: (context-aware) phrase polishing, sentence paraphrasing, and sentence expansion, whereas many other writing assistants often support one or two functions in this category. The main contents of this report include major modules of Effidit, methods for implementing these modules, and evaluation results of some key methods.

Yifan Wang, Qingyan Guo, Xinzhe Ni et al.

In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks. However, under the standard ICL setting, LLMs may sometimes neglect query-related information in demonstrations, leading to incorrect predictions. To address this limitation, we propose a new paradigm called Hint-enhanced In-Context Learning (HICL) to explore the power of ICL in open-domain question answering, an important form in knowledge-intensive tasks. HICL leverages LLMs' reasoning ability to extract query-related knowledge from demonstrations, then concatenates the knowledge to prompt LLMs in a more explicit way. Furthermore, we track the source of this knowledge to identify specific examples, and introduce a Hint-related Example Retriever (HER) to select informative examples for enhanced demonstrations. We evaluate HICL with HER on 3 open-domain QA benchmarks, and observe average performance gains of 2.89 EM score and 2.52 F1 score on gpt-3.5-turbo, 7.62 EM score and 7.27 F1 score on LLaMA-2-Chat-7B compared with standard setting.

Jiawei Zhou, Hang Ding, Haiyun Jiang

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework for knowledge-intensive tasks, yet its effectiveness in long-context scenarios is often bottlenecked by the retriever's inability to distinguish sparse yet crucial evidence. Standard retrievers, optimized for query-document similarity, frequently fail to align with the downstream goal of generating a precise answer. To bridge this gap, we propose a novel fine-tuning framework that optimizes the retriever for Answer Alignment. Specifically, we first identify high-quality positive chunks by evaluating their sufficiency to generate the correct answer. We then employ a curriculum-based contrastive learning scheme to fine-tune the retriever. This curriculum leverages LLM-constructed Knowledge Graphs (KGs) to generate augmented queries, which in turn mine progressively challenging hard negatives. This process trains the retriever to distinguish the answer-sufficient positive chunks from these nuanced distractors, enhancing its generalization. Extensive experiments on 10 datasets from the Ultradomain and LongBench benchmarks demonstrate that our fine-tuned retriever achieves state-of-the-art performance, improving 14.5\% over the base model without substantial architectural modifications and maintaining strong efficiency for long-context RAG. Our work presents a robust and effective methodology for building truly answer-centric retrievers. Source Code is available on https://github.com/valleysprings/ARK/.

Mao Yan Chen, Haiyun Jiang, Yujiu Yang

The short text matching task employs a model to determine whether two short texts have the same semantic meaning or intent. Existing short text matching models usually rely on the content of short texts which are lack information or missing some key clues. Therefore, the short texts need external knowledge to complete their semantic meaning. To address this issue, we propose a new short text matching framework for introducing external knowledge to enhance the short text contextual representation. In detail, we apply a self-attention mechanism to enrich short text representation with external contexts. Experiments on two Chinese datasets and one English dataset demonstrate that our framework outperforms the state-of-the-art short text matching models.

Tinghui Zhu, Jingping Liu, Jiaqing Liang et al.

Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual semantics, leading to an inability to generalize to unseen terms and the "Prototypical Hypernym Problem." In this paper, we propose Visual Taxonomy Expansion (VTE), introducing visual features into the taxonomy expansion task. We propose a textual hypernymy learning task and a visual prototype learning task to cluster textual and visual semantics. In addition to the tasks on respective modalities, we introduce a hyper-proto constraint that integrates textual and visual semantics to produce fine-grained visual semantics. Our method is evaluated on two datasets, where we obtain compelling results. Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8.75 %. Additionally, our approach performs better than ChatGPT on the Chinese taxonomy dataset.

Yi Chen, Haiyun Jiang, Wei Bi et al.

This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings. Different from existing insertion-based writing assistance tasks, TE requires the model to be more flexible in both locating and generation, and also more cautious in keeping basic semantics. We leverage four complementary approaches to construct a dataset with 12 million automatically generated instances and 2K human-annotated references for both English and Chinese. To facilitate automatic evaluation, we design various metrics from multiple perspectives. In particular, we propose Info-Gain to effectively measure the informativeness of expansions, which is an important quality dimension in TE. On top of a pre-trained text-infilling model, we build both pipelined and joint Locate&Infill models, which demonstrate the superiority over the Text2Text baselines, especially in expansion informativeness. Experiments verify the feasibility of the TE task and point out potential directions for future research toward better automatic text expansion.

Lingfeng Shen, Haiyun Jiang, Lemao Liu et al.

Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks. The recent breakthrough in sentence embedding is achieved by pre-trained language models (PLMs). Despite its success, an embedded vector (Sen2Vec) representing a point estimate does not naturally express uncertainty in a taskagnostic way. This paper thereby proposes an efficient framework on probabilistic sentence embedding (Sen2Pro) from PLMs, and it represents a sentence as a probability density distribution in an embedding space to reflect both model uncertainty and data uncertainty (i.e., many-to-one nature) in the sentence representation. The proposed framework performs in a plug-and-play way without retraining PLMs anymore, and it is easy to implement and generally applied on top of any PLM. The superiority of Sen2Pro over Sen2Vec has been theoretically verified and practically illustrated on different NLP tasks.

Chang Gao, Haiyun Jiang, Deng Cai et al.

Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other instances and lack task-level consistency across the selected few-shot examples. To address these limitations, we propose a comprehensive framework, StrategyLLM, allowing LLMs to perform inductive reasoning, deriving general strategies from specific task instances, and deductive reasoning, applying these general strategies to particular task examples, for constructing generalizable and consistent few-shot prompts. It employs four LLM-based agents: strategy generator, executor, optimizer, and evaluator, working together to generate, evaluate, and select promising strategies for a given task. Experimental results demonstrate that StrategyLLM outperforms the competitive baseline CoT-SC that requires human-annotated solutions on 13 datasets across 4 challenging tasks without human involvement, including math reasoning (34.2\% $\rightarrow$ 38.8\%), commonsense reasoning (70.3\% $\rightarrow$ 72.5\%), algorithmic reasoning (73.7\% $\rightarrow$ 85.0\%), and symbolic reasoning (30.0\% $\rightarrow$ 79.2\%). Further analysis reveals that StrategyLLM is applicable to various LLMs and demonstrates advantages across numerous scenarios.

Lingfeng Shen, Ze Zhang, Haiyun Jiang et al.

Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial sentences from benign ones. However, {the core limitation of previous detection methods is being incapable of giving correct predictions on adversarial sentences unlike defense methods from other paradigms.} To solve this issue, this paper proposes TextShield: (1) we discover a link between text attack and saliency information, and then we propose a saliency-based detector, which can effectively detect whether an input sentence is adversarial or not. (2) We design a saliency-based corrector, which converts the detected adversary sentences to benign ones. By combining the saliency-based detector and corrector, TextShield extends the detection-only paradigm to a detection-correction paradigm, thus filling the gap in the existing detection-based defense. Comprehensive experiments show that (a) TextShield consistently achieves higher or comparable performance than state-of-the-art defense methods across various attacks on different benchmarks. (b) our saliency-based detector outperforms existing detectors for detecting adversarial sentences.

Chaoyang Wang, Zeyu Zhang, Meng Meng et al.

Visual reasoning is crucial for understanding complex multimodal data and advancing Artificial General Intelligence. Existing methods enhance the reasoning capability of Multimodal Large Language Models (MLLMs) through Reinforcement Learning (RL) fine-tuning (e.g., GRPO). However, current RL approaches sample action groups solely from the policy model itself, which limits the upper boundary of the model's reasoning capability and leads to inefficient training. To address these limitations, this paper proposes a novel RL framework called \textbf{Vision-EKIPL}. The core of this framework lies in introducing high-quality actions generated by external auxiliary models during the RL training process to guide the optimization of the policy model. The policy learning with knowledge infusion from external models significantly expands the model's exploration space, effectively improves the reasoning boundary, and substantially accelerates training convergence speed and efficiency. Experimental results demonstrate that our proposed Vision-EKIPL achieved up to a 5\% performance improvement on the Reason-RFT-CoT Benchmark compared to the state-of-the-art (SOTA). It reveals that Vision-EKIPL can overcome the limitations of traditional RL methods, significantly enhance the visual reasoning performance of MLLMs, and provide a new effective paradigm for research in this field.

Zhongshen Zeng, Pengguang Chen, Shu Liu et al.

In this work, we introduce a novel evaluation paradigm for Large Language Models (LLMs) that compels them to transition from a traditional question-answering role, akin to a student, to a solution-scoring role, akin to a teacher. This paradigm, focusing on "reasoning about reasoning," hence termed meta-reasoning, shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation that effectively distinguishes between the cognitive capabilities of different models. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark. Our extensive analysis includes several state-of-the-art models from both open-source and commercial domains, uncovering fundamental deficiencies in their training and evaluation methodologies. Notably, while models like Deepseek-v2 and Claude3-Sonnet closely competed with GPT-4 in GSM8K, their performance disparities expanded dramatically in MR-GSM8K, with differences widening to over 20 absolute points, underscoring the significant challenge posed by our meta-reasoning approach.

Linghao Zhang, Jungang Li, Yonghua Hei et al.

Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of visual capabilities, particularly the balance between spatial and temporal understanding, remains poorly understood. In this paper, we systematically study how Video-SFT reshapes visual capabilities in MLLMs. Across architectures, parameter scales, and frame sampling settings, we observe a consistent pattern: Video-SFT reliably improves video performance, but often yields limited gains or even degradation on static image benchmarks. We further show that this trade-off is closely tied to temporal budget: increasing the number of sampled frames generally improves video performance, but does not reliably improve static image performance. Motivated by this finding, we study an instruction-aware Hybrid-Frame strategy that adaptively allocates frame counts and partially mitigates the image-video trade-off. Our results indicate that Video-SFT is not a free lunch for MLLMs, and preserving spatial understanding remains a central challenge in joint image-video training.

Jingping Liu, Ziyan Liu, Zhedong Cen et al.

Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git.

Daiqiang Li, Zihao Pan, Zeyu Zhang et al.

In recent years, GUI visual agents built upon Multimodal Large Language Models (MLLMs) have demonstrated strong potential in navigation tasks. However, high-resolution GUI screenshots produce a large number of visual tokens, making the direct preservation of complete historical information computationally expensive. In this paper, we conduct an empirical study on token pruning for historical screenshots in GUI scenarios and distill three practical insights that are crucial for designing effective pruning strategies. First, we observe that GUI screenshots exhibit a distinctive foreground-background semantic composition. To probe this property, we apply a simple edge-based separation to partition screenshots into foreground and background regions. Surprisingly, we find that, contrary to the common assumption that background areas have little semantic value, they effectively capture interface-state transitions, thereby providing auxiliary cues for GUI reasoning. Second, compared with carefully designed pruning strategies, random pruning possesses an inherent advantage in preserving spatial structure, enabling better performance under the same computational budget. Finally, we observe that GUI Agents exhibit a recency effect similar to human cognition: by allocating larger token budgets to more recent screenshots and heavily compressing distant ones, we can significantly reduce computational cost while maintaining nearly unchanged performance. These findings offer new insights and practical guidance for the design of efficient GUI visual agents.

Ruizhou Li, Haiyun Jiang

Recent advances in Vision-Language Models (VLMs) have shown promising capabilities in interpreting visualized graph data, offering a new perspective for graph-structured reasoning beyond traditional Graph Neural Networks (GNNs). However, existing studies focus primarily on single-graph reasoning, leaving the critical challenge of multi-graph joint reasoning underexplored. In this work, we introduce the first comprehensive benchmark designed to evaluate and enhance the multi-graph reasoning abilities of VLMs. Our benchmark covers four common graph types-knowledge graphs, flowcharts, mind maps, and route maps-and supports both homogeneous and heterogeneous graph groupings with tasks of increasing complexity. We evaluate several state-of-the-art VLMs under a multi-dimensional scoring framework that assesses graph parsing, reasoning consistency, and instruction-following accuracy. Additionally, we fine-tune multiple open-source models and observe consistent improvements, confirming the effectiveness of our dataset. This work provides a principled step toward advancing multi-graph understanding and reveals new opportunities for cross-modal graph intelligence.

Xinhan Zheng, Huyu Wu, Xueting Wang et al.

Multimodal large language models (MLLMs) exhibit a pronounced preference for textual inputs when processing vision-language data, limiting their ability to reason effectively from visual evidence. Unlike prior studies that attribute this text bias to external factors such as data imbalance or instruction tuning, we propose that the bias originates from the model's internal architecture. Specifically, we hypothesize that visual key vectors (Visual Keys) are out-of-distribution (OOD) relative to the text key space learned during language-only pretraining. Consequently, these visual keys receive systematically lower similarity scores during attention computation, leading to their under-utilization in the context representation. To validate this hypothesis, we extract key vectors from LLaVA and Qwen2.5-VL and analyze their distributional structures using qualitative (t-SNE) and quantitative (Jensen-Shannon divergence) methods. The results provide direct evidence that visual and textual keys occupy markedly distinct subspaces within the attention space. The inter-modal divergence is statistically significant, exceeding intra-modal variation by several orders of magnitude. These findings reveal that text bias arises from an intrinsic misalignment within the attention key space rather than solely from external data factors.

Jiaqi Li, Miaozeng Du, Chuanyi Zhang et al.

Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving the intricacies of fine-grained (FG) multimodal entity knowledge largely unexplored. This gap presents a notable challenge, as FG entity recognition is pivotal for the practical deployment and effectiveness of MLLMs in diverse real-world scenarios. To bridge this gap, we introduce MIKE, a comprehensive benchmark and dataset specifically designed for the FG multimodal entity knowledge editing. MIKE encompasses a suite of tasks tailored to assess different perspectives, including Vanilla Name Answering, Entity-Level Caption, and Complex-Scenario Recognition. In addition, a new form of knowledge editing, Multi-step Editing, is introduced to evaluate the editing efficiency. Through our extensive evaluations, we demonstrate that the current state-of-the-art methods face significant challenges in tackling our proposed benchmark, underscoring the complexity of FG knowledge editing in MLLMs. Our findings spotlight the urgent need for novel approaches in this domain, setting a clear agenda for future research and development efforts within the community.

Bolun Sun, Yifan Zhou, Haiyun Jiang

This paper presents a novel application of large language models (LLMs) to enhance user comprehension of privacy policies through an interactive dialogue agent. We demonstrate that LLMs significantly outperform traditional models in tasks like Data Practice Identification, Choice Identification, Policy Summarization, and Privacy Question Answering, setting new benchmarks in privacy policy analysis. Building on these findings, we introduce an innovative LLM-based agent that functions as an expert system for processing website privacy policies, guiding users through complex legal language without requiring them to pose specific questions. A user study with 100 participants showed that users assisted by the agent had higher comprehension levels (mean score of 2.6 out of 3 vs. 1.8 in the control group), reduced cognitive load (task difficulty ratings of 3.2 out of 10 vs. 7.8), increased confidence in managing privacy, and completed tasks in less time (5.5 minutes vs. 15.8 minutes). This work highlights the potential of LLM-based agents to transform user interaction with privacy policies, leading to more informed consent and empowering users in the digital services landscape.

Jincheng Dai, Zhuowei Huang, Haiyun Jiang et al.

Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory used by the KV cache rises linearly with sequence length, becoming a primary bottleneck for inference. In this paper, we introduce an innovative method for optimizing the KV cache, which considerably minimizes its memory footprint. Upon thorough investigation, we discover that in most Transformer models, (i) there is a striking similarity between adjacent tokens' query vectors, and (ii) the attention calculation of the current query can rely exclusively on the attention information of a small fraction of preceding queries. Based on these observations, we present CORM, a KV cache eviction policy that dynamically retains essential key-value pairs for inference without the need for model fine-tuning. Our validation shows that CORM reduces the inference memory usage of KV cache by up to 70\% with negligible performance degradation across six tasks in LongBench. Furthermore, we demonstrate that CORM is compatible with GQA for further compression rate.

Huyu Wu, Meng Tang, Xinhan Zheng et al.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a diverse range of multimodal tasks. However, these models suffer from a core problem known as text dominance: they depend heavily on text for their inference, while underutilizing other modalities. While prior work has acknowledged this phenomenon in vision-language tasks, often attributing it to data biases or model architectures. In this paper, we conduct the first systematic investigation of text dominance across diverse data modalities, including images, videos, audio, time-series, and graphs. To measure this imbalance, we propose two evaluation metrics: the Modality Dominance Index (MDI) and the Attention Efficiency Index (AEI). Our comprehensive analysis reveals that text dominance is both significant and pervasive across all tested modalities. Our in-depth analysis identifies three underlying causes: attention dilution from severe token redundancy in non-textual modalities, the influence of fusion architecture design, and task formulations that implicitly favor textual inputs. Furthermore, we propose a simple token compression method that effectively rebalances model attention. Applying this method to LLaVA-7B, for instance, drastically reduces its MDI from 10.23 to a well-balanced value of 0.86. Our analysis and methodological framework offer a foundation for the development of more equitable and comprehensive multimodal language models.

Nan Wang, Yongqi Fan, yansha zhu et al.

Large Language Models (LLMs) face challenges in knowledge-intensive reasoning tasks like classic multi-hop question and answering, which involves reasoning across multiple facts. This difficulty arises because the chain of thoughts (CoTs) generated by LLMs in such tasks often deviate from real or a priori reasoning paths. In contrast, knowledge graphs (KGs) explicitly represent the logical connections between facts through entities and relationships. This reflects a significant gap. Meanwhile, large reasoning models (LRMs), such as o1, have demonstrated that long-step reasoning significantly enhances the performance of LLMs. Building on these insights, we propose KG-o1, a four-stage approach that integrates KGs to enhance the multi-hop reasoning abilities of LLMs. We first filter out initial entities and generate complex subgraphs. Secondly, we construct logical paths for subgraphs and then use knowledge graphs to build a dataset with a complex and extended brainstorming process, which trains LLMs to imitate long-term reasoning. Finally, we employ rejection sampling to generate a self-improving corpus for direct preference optimization (DPO), further refining the LLMs reasoning abilities. We conducted experiments on two simple and two complex datasets. The results show that KG-o1 models exhibit superior performance across all tasks compared to existing LRMs.

Qihang Ai, Jianwu Zhou, Haiyun Jiang et al.

Graph data is ubiquitous in the physical world, and it has always been a challenge to efficiently model graph structures using a unified paradigm for the understanding and reasoning on various graphs. Moreover, in the era of large language models, integrating complex graph information into text sequences has become exceptionally difficult, which hinders the ability to interact with graph data through natural language instructions.The paper presents a new paradigm for understanding and reasoning about graph data by integrating image encoding and multimodal technologies. This approach enables the comprehension of graph data through an instruction-response format, utilizing GPT-4V's advanced capabilities. The study evaluates this paradigm on various graph types, highlighting the model's strengths and weaknesses, particularly in Chinese OCR performance and complex reasoning tasks. The findings suggest new direction for enhancing graph data processing and natural language interaction.

Chenglizhao Chen, Shaofeng Liang, Runwei Guan et al.

Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method.

Qihang Ai, Haiyun Jiang

We study reasoning tasks through a framework that integrates auto-regressive (AR) and non-autoregressive (NAR) language models. AR models, which generate text sequentially, excel at producing coherent outputs but often suffer from slow inference, particularly in reasoning-intensive domains such as mathematics and code, where lengthy chains of thought are required. In contrast, NAR models, such as discrete diffusion models, allow parallel generation and offer substantial speedups, though typically at the cost of reduced output quality. To address these limitations, we introduce a new paradigm in which an NAR model efficiently produces intermediate reasoning traces, which subsequently guide an AR model to deliver precise final answers. Experiments demonstrate that our approach yields significant 26% improvements over strong baselines while substantially reducing inference cost.

Lingfeng Shen, Haiyun Jiang, Lemao Liu et al.

Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than static word embeddings. Although dimension is a key factor determining the quality of static word embeddings, automatic dimension selection is rarely discussed. In this paper, we investigate the impact of word frequency on the dimension selection, and empirically find that word frequency is so vital that it needs to be taken into account during dimension selection. Based on such an empirical finding, this paper proposes a dimension selection method that uses a metric (Mixed Product Distance, MPD) to select a proper dimension for word embedding algorithms without training any word embedding. Through applying a post-processing function to oracle matrices, the MPD-based method can de-emphasize the impact of word frequency. Experiments on both context-unavailable and context-available tasks demonstrate the better efficiency-performance trade-off of our MPD-based dimension selection method over baselines.

Lingfeng Shen, Haiyun Jiang, Lemao Liu et al.

Generating proper embedding of sentences through an unsupervised way is beneficial to semantic matching and retrieval problems in real-world scenarios. This paper presents Representation ALchemy (RepAL), an extremely simple post-processing method that enhances sentence representations. The basic idea in RepAL is to de-emphasize redundant information of sentence embedding generated by pre-trained models. Through comprehensive experiments, we show that RepAL is free of training and is a plug-and-play method that can be combined with most existing unsupervised sentence learning models. We also conducted in-depth analysis to understand RepAL.

Lingfeng Shen, Lemao Liu, Haiyun Jiang et al.

In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance than their reference-based counterparts. (2) Most commonly used metrics do not align well with human annotation. Underlying reasons behind the above findings are explored through additional experiments and in-depth analyses. Based on the experiments and analyses, we propose ParaScore, a new evaluation metric for paraphrase generation. It possesses the merits of reference-based and reference-free metrics and explicitly models lexical divergence. Experimental results demonstrate that ParaScore significantly outperforms existing metrics.

Lingfeng Shen, Haiyun Jiang, Lemao Liu et al.

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threatening backdoor attack is the stealthy backdoor, which defines the triggers as text style or syntactic. Although they have achieved an incredible high attack success rate (ASR), we find that the principal factor contributing to their ASR is not the `backdoor trigger' paradigm. Thus the capacity of these stealthy backdoor attacks is overestimated when categorized as backdoor attacks. Therefore, to evaluate the real attack power of backdoor attacks, we propose a new metric called attack successful rate difference (ASRD), which measures the ASR difference between clean state and poison state models. Besides, since the defenses against stealthy backdoor attacks are absent, we propose Trigger Breaker, consisting of two too simple tricks that can defend against stealthy backdoor attacks effectively. Experiments show that our method achieves significantly better performance than state-of-the-art defense methods against stealthy backdoor attacks.

Jiayang Cheng, Haiyun Jiang, Deqing Yang et al.

Relation extraction is an important task in knowledge acquisition and text understanding. Existing works mainly focus on improving relation extraction by extracting effective features or designing reasonable model structures. However, few works have focused on how to validate and correct the results generated by the existing relation extraction models. We argue that validation is an important and promising direction to further improve the performance of relation extraction. In this paper, we explore the possibility of using question answering as validation. Specifically, we propose a novel question-answering based framework to validate the results from relation extraction models. Our proposed framework can be easily applied to existing relation classifiers without any additional information. We conduct extensive experiments on the popular NYT dataset to evaluate the proposed framework, and observe consistent improvements over five strong baselines.

Haisong Zhang, Lemao Liu, Haiyun Jiang et al.

This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human annotation efforts. The main contents of this report include major functions of TexSmart, algorithms for achieving these functions, how to use the TexSmart toolkit and Web APIs, and evaluation results of some key algorithms.

Zhendong Chu, Haiyun Jiang, Yanghua Xiao et al.

Distant supervision makes it possible to automatically label bags of sentences for relation extraction by leveraging knowledge bases, but suffers from the sparse and noisy bag issues. Additional information sources are urgently needed to supplement the training data and overcome these issues. In this paper, we introduce two widely-existing sources in knowledge bases, namely entity descriptions, and multi-grained entity types to enrich the distantly supervised data. We see information sources as multiple views and fusing them to construct an intact space with sufficient information. An end-to-end multi-view learning framework is proposed for relation extraction via Intact Space Representation Learning (InSRL), and the representations of single views are jointly learned simultaneously. Moreover, inner-view and cross-view attention mechanisms are used to highlight important information on different levels on an entity-pair basis. The experimental results on a popular benchmark dataset demonstrate the necessity of additional information sources and the effectiveness of our framework. We will release the implementation of our model and dataset with multiple information sources after the anonymized review phase.

Haiyun Jiang, Qiaoben Bao, Qiao Cheng et al.

Relation extraction aims to identify the target relations of entities in texts. Relation extraction is very important for knowledge base construction and text understanding. Traditional binary relation extraction, including supervised, semi-supervised and distant supervised ones, has been extensively studied and significant results are achieved. In recent years, many complex relation extraction tasks, i.e., the variants of simple binary relation extraction, are proposed to meet the complex applications in practice. However, there is no literature to fully investigate and summarize these complex relation extraction works so far. In this paper, we first report the recent progress in traditional simple binary relation extraction. Then we summarize the existing complex relation extraction tasks and present the definition, recent progress, challenges and opportunities for each task.

Jiangjie Chen, Ao Wang, Haiyun Jiang et al.

A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity. Entities in most knowledge graphs (KGs) still lack such descriptions, thus calling for automatic methods to supplement such information. However, existing generative methods either overlook the grammatical structure or make factual mistakes in generated texts. To solve these problems, we propose a head-modifier template-based method to ensure the readability and data fidelity of generated type descriptions. We also propose a new dataset and two automatic metrics for this task. Experiments show that our method improves substantially compared with baselines and achieves state-of-the-art performance on both datasets.

Jindong Chen, Yizhou Hu, Jingping Liu et al.

Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough contextual information, which poses a great challenge for classification. In this paper, we retrieve knowledge from external knowledge source to enhance the semantic representation of short texts. We take conceptual information as a kind of knowledge and incorporate it into deep neural networks. For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA). We utilize Concept towards Short Text (C- ST) attention and Concept towards Concept Set (C-CS) attention to acquire the weight of concepts from two aspects. And we classify a short text with the help of conceptual information. Unlike traditional approaches, our model acts like a human being who has intrinsic ability to make decisions based on observation (i.e., training data for machines) and pays more attention to important knowledge. We also conduct extensive experiments on four public datasets for different tasks. The experimental results and case studies show that our model outperforms the state-of-the-art methods, justifying the effectiveness of knowledge powered attention.