Xuanang Chen

Qiming Zhu, Jialun Cao, Xuanang Chen et al.

Current research on large language models (LLMs) with retrieval-augmented code generation (RACG) has largely focused on single-language settings, leaving their cross-lingual effectiveness underexplored. Multilingual RACG systems are increasingly important for migrating and reusing code across programming languages (PLs), a common yet challenging task in modern software development. To systematically study cross-lingual code knowledge transfer in RACG, we construct a dataset covering 13 PLs with nearly 14K instances. Our experiments reveal three key insights: (1) Knowledge transfer in RACG across PLs is non-trivial even using direct injection. (2) RACG exhibits unequal cross-lingual knowledge transfer, and its efficacy depends on linguistic affinity of PL pair and diversity of LLM pretraining corpus. (3) RACG shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever. These findings provide practical guidance for designing effective multilingual RACG systems. https://github.com/icip-cas/Cross-Lingual-RACG

Hao Zheng, Guozhao Mo, Xinru Yan et al.

Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent

Zichao Li, Aizier Abulaiti, Yaojie Lu et al.

Document Structured Extraction (DSE) aims to extract structured content from raw documents. Despite the emergence of numerous DSE systems, their unified evaluation remains inadequate, significantly hindering the field's advancement. This problem is largely attributed to existing benchmark paradigms, which exhibit fragmented and localized characteristics. To address these limitations and offer a thorough evaluation of DSE systems, we introduce a novel benchmark named READoc, which defines DSE as a realistic task of converting unstructured PDFs into semantically rich Markdown. The READoc dataset is derived from 3,576 diverse and real-world documents from arXiv, GitHub, and Zenodo. In addition, we develop a DSE Evaluation S$^3$uite comprising Standardization, Segmentation and Scoring modules, to conduct a unified evaluation of state-of-the-art DSE approaches. By evaluating a range of pipeline tools, expert visual models, and general VLMs, we identify the gap between current work and the unified, realistic DSE objective for the first time. We aspire that READoc will catalyze future research in DSE, fostering more comprehensive and practical solutions.

Xuanang Chen, Ben He, Le Sun et al.

Neural ranking models (NRMs) have undergone significant development and have become integral components of information retrieval (IR) systems. Unfortunately, recent research has unveiled the vulnerability of NRMs to adversarial document manipulations, potentially exploited by malicious search engine optimization practitioners. While progress in adversarial attack strategies aids in identifying the potential weaknesses of NRMs before their deployment, the defensive measures against such attacks, like the detection of adversarial documents, remain inadequately explored. To mitigate this gap, this paper establishes a benchmark dataset to facilitate the investigation of adversarial ranking defense and introduces two types of detection tasks for adversarial documents. A comprehensive investigation of the performance of several detection baselines is conducted, which involve examining the spamicity, perplexity, and linguistic acceptability, and utilizing supervised classifiers. Experimental results demonstrate that a supervised classifier can effectively mitigate known attacks, but it performs poorly against unseen attacks. Furthermore, such classifier should avoid using query text to prevent learning the classification on relevance, as it might lead to the inadvertent discarding of relevant documents.

Ying Zhou, Xuanang Chen, Ben He et al.

Knowledge graph completion (KGC) aims to infer missing knowledge triples based on known facts in a knowledge graph. Current KGC research mostly follows an entity ranking protocol, wherein the effectiveness is measured by the predicted rank of a masked entity in a test triple. The overall performance is then given by a micro(-average) metric over all individual answer entities. Due to the incomplete nature of the large-scale knowledge bases, such an entity ranking setting is likely affected by unlabelled top-ranked positive examples, raising questions on whether the current evaluation protocol is sufficient to guarantee a fair comparison of KGC systems. To this end, this paper presents a systematic study on whether and how the label sparsity affects the current KGC evaluation with the popular micro metrics. Specifically, inspired by the TREC paradigm for large-scale information retrieval (IR) experimentation, we create a relatively "complete" judgment set based on a sample from the popular FB15k-237 dataset following the TREC pooling method. According to our analysis, it comes as a surprise that switching from the original labels to our "complete" labels results in a drastic change of system ranking of a variety of 13 popular KGC models in terms of micro metrics. Further investigation indicates that the IR-like macro(-average) metrics are more stable and discriminative under different settings, meanwhile, less affected by label sparsity. Thus, for KGC evaluation, we recommend conducting TREC-style pooling to balance between human efforts and label completeness, and reporting also the IR-like macro metrics to reflect the ranking nature of the KGC task.

Fangan Dong, Zuming Yan, Xuri Ge et al.

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical efficiency. In this work, we first show that a small subset of neurons in LLMs exhibits strong predictive correlations with reasoning correctness. Based on this observation, we propose AdaRAS (Adaptive Reasoning Activation Steering), a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations. AdaRAS identifies Reasoning-Critical Neurons (RCNs) via a polarity-aware mean-difference criterion and adaptively steers their activations during inference, enhancing incorrect reasoning traces while avoiding degradation on already-correct cases. Experiments on 10 mathematics and coding benchmarks demonstrate consistent improvements, including over 13% gains on AIME-24 and AIME-25. Moreover, AdaRAS exhibits strong transferability across datasets and scalability to stronger models, outperforming post-training methods without additional training or sampling cost.

Qingyu Zhang, Chunlei Xin, Xuanang Chen et al.

Goal-driven persuasive dialogue, exemplified by applications like telemarketing, requires sophisticated multi-turn planning and strict factual faithfulness, which remains a significant challenge for even state-of-the-art Large Language Models (LLMs). A lack of task-specific data often limits previous works, and direct LLM application suffers from strategic brittleness and factual hallucination. In this paper, we first construct and release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain. We then propose AI-Salesman, a novel framework featuring a dual-stage architecture. For the training stage, we design a Bayesian-supervised reinforcement learning algorithm that learns robust sales strategies from noisy dialogues. For the inference stage, we introduce the Dynamic Outline-Guided Agent (DOGA), which leverages a pre-built script library to provide dynamic, turn-by-turn strategic guidance. Moreover, we design a comprehensive evaluation framework that combines fine-grained metrics for key sales skills with the LLM-as-a-Judge paradigm. Experimental results demonstrate that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations, showcasing its effectiveness in complex persuasive scenarios.

Shuainan Liu, Xuanang Chen, Ben He et al.

Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limited set of related or neighboring knowledge. While effective, such evaluations remain confined to finite, dataset-bounded samples, leaving the broader impact of editing on the model's knowledge system insufficiently understood. To address this gap, we introduce Embedding-Virtualized Knowledge (EVK) that characterizes model knowledge through controlled perturbations in embedding space, enabling the exploration of a substantially broader and virtualized knowledge region beyond explicit data annotations. Based on EVK, we construct an embedding-level evaluation benchmark EVK-Bench that quantifies potential knowledge drift induced by editing, revealing effects that are not captured by conventional sample-based metrics. Furthermore, we propose a plug-and-play EVK-Align module that constrains embedding-level knowledge drift during editing and can be seamlessly integrated into existing editing methods. Experiments demonstrate that our approach enables more comprehensive evaluation while significantly improving knowledge preservation without sacrificing editing accuracy.

Guozhao Mo, Wenliang Zhong, Jiawei Chen et al.

With the rapid development of Model Context Protocol (MCP), the number of MCP servers has surpassed 10,000. However, existing MCP benchmarks are limited to single-server settings with only a few tools, hindering effective evaluation of agent capabilities in large-scale, real-world scenarios. To address this limitation, we present LiveMCPBench, the first comprehensive benchmark comprising 95 real-world tasks grounded in the MCP ecosystem, designed to evaluate LLM agents at scale across diverse servers. To support a scalable and reproducible evaluation pipeline in large-scale MCP environments, we curate LiveMCPTool, a diverse and readily deployable collection of 70 MCP servers and 527 tools. Furthermore, we introduce LiveMCPEval, an LLM-as-a-Judge framework that enables automated and adaptive evaluation in dynamic, time-varying task environments, achieving 81% agreement with human reviewers. Finally, we propose the MCP Copilot Agent, a multi-step agent that routes tools for dynamic planning and executes tools for API interaction across the entire LiveMCPTool suite. Our evaluation covers 10 leading models, with the best-performing model (Claude-Sonnet-4) reaching a 78.95% success rate. However, we observe large performance variance across models, and several widely-used models perform poorly in LiveMCPBench's complex, tool-rich environments. Overall, LiveMCPBench offers the first unified framework for benchmarking LLM agents in realistic, tool-rich, and dynamic MCP environments, laying a solid foundation for scalable and reproducible research on agent capabilities. Our code and data will be publicly available at https://icip-cas.github.io/LiveMCPBench.

Dan Wang, Guozhao Mo, Yafei Shi et al.

Multilingual Retrieval-Augmented Generation (mRAG) leverages cross-lingual evidence to ground Large Language Models (LLMs) in global knowledge. However, we show that current mRAG systems suffer from a language bias during reranking, systematically favoring English and the query's native language. By introducing an estimated oracle evidence analysis, we quantify a substantial performance gap between existing rerankers and the achievable upper bound. Further analysis reveals a critical distributional mismatch: while optimal predictions require evidence scattered across multiple languages, current systems systematically suppress such ``answer-critical'' documents, thereby limiting downstream generation performance. To bridge this gap, we propose \textit{\textbf{L}anguage-\textbf{A}gnostic \textbf{U}tility-driven \textbf{R}eranker \textbf{A}lignment (LAURA)}, which aligns multilingual evidence ranking with downstream generative utility. Experiments across diverse languages and generation models show that LAURA effectively mitigates language bias and consistently improves mRAG performance.

Yihan Chen, Jiawei Chen, Guozhao Mo et al.

The growing integration of large language models (LLMs) into the peer review process presents potential risks to the fairness and reliability of scholarly evaluation. While LLMs offer valuable assistance for reviewers with language refinement, there is growing concern over their use to generate substantive review content. Existing general AI-generated text detectors are vulnerable to paraphrasing attacks and struggle to distinguish between surface language refinement and substantial content generation, suggesting that they primarily rely on stylistic cues. When applied to peer review, this limitation can result in unfairly suspecting reviews with permissible AI-assisted language enhancement, while failing to catch deceptively humanized AI-generated reviews. To address this, we propose a paradigm shift from style-based to content-based detection. Specifically, we introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews, covering six distinct modes of human-AI collaboration. Furthermore, we develop CoCoDet, an AI review detector via a multi-task learning framework, designed to achieve more accurate and robust detection of AI involvement in review content. Our work offers a practical foundation for evaluating the use of LLMs in peer review, and contributes to the development of more precise, equitable, and reliable detection methods for real-world scholarly applications. Our code and data will be publicly available at https://github.com/Y1hanChen/COCONUTS.

Zhuoqun Li, Xuanang Chen, Hongyu Lin et al.

Paper search is an important activity for researchers, typically involving using a query with description of a topic to find relevant papers. As research deepens, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than being limited to coarse-grained topics. However, previous paper search systems are unable to meet these flexible-grained requirements, as these systems mainly collect paper abstracts to construct index of corpus, which lack detailed information to support retrieval by finer-grained queries. In this work, we propose PaperRegister, consisted of offline hierarchical indexing and online adaptive retrieval, transforming traditional abstract-based index into hierarchical index tree for paper search, thereby supporting queries at flexible granularity. Experiments on paper search tasks across a range of granularity demonstrate that PaperRegister achieves the state-of-the-art performance, and particularly excels in fine-grained scenarios, highlighting the good potential as an effective solution for flexible-grained paper search in real-world applications. Code for this work is in https://github.com/Li-Z-Q/PaperRegister.

Tianyun Zhong, Guozhao Mo, Yanjiang Liu et al.

With the emergence of large language models (LLMs), there is an expectation that LLMs can effectively extract explicit information from complex real-world documents (e.g., papers, reports). However, most LLMs generate paragraph-style answers that are chaotic, disorganized, and untraceable. To bridge this gap, we introduce the Arranged and Organized Extraction Benchmark (AOE), a new bilingual benchmark with data and documents of varying lengths designed to systematically evaluate the ability of LLMs to comprehend fragmented documents and reconstruct isolated information into one organized table. Unlike conventional text-to-table tasks, which rely on fixed schema and narrow task domains, AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries. In the experiment, we evaluated both open-source and closed-source state-of-the-art LLMs. The results show that even the most advanced models struggled significantly. The benchmark is available at https://anonymous.4open.science/r/AOE-Benchmark/.

Zhuoqun Li, Xuanang Chen, Haiyang Yu et al.

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-intensive reasoning, we proposes a new framework, StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Extensive experiments across various knowledge-intensive tasks show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios, demonstrating its potential as an effective solution for enhancing LLMs in complex real-world applications.

Shuaimin Li, Xuanang Chen, Yuanfeng Song et al.

Data visualization (DV) systems are increasingly recognized for their profound capability to uncover insights from vast datasets, gaining attention across both industry and academia. Crafting data queries is an essential process within certain declarative visualization languages (DVLs, e.g., Vega-Lite, EChart.). The evolution of natural language processing (NLP) technologies has streamlined the use of natural language interfaces to visualize tabular data, offering a more accessible and intuitive user experience. However, current methods for converting natural language questions into data visualization queries, such as Seq2Vis, ncNet, and RGVisNet, despite utilizing complex neural network architectures, still fall short of expectations and have great room for improvement. Large language models (LLMs) such as ChatGPT and GPT-4, have established new benchmarks in a variety of NLP tasks, fundamentally altering the landscape of the field. Inspired by these advancements, we introduce a novel framework, Prompt4Vis, leveraging LLMs and in-context learning to enhance the performance of generating data visualization from natural language. Prompt4Vis comprises two key components: (1) a multi-objective example mining module, designed to find out the truly effective examples that strengthen the LLM's in-context learning capabilities for text-to-vis; (2) a schema filtering module, which is proposed to simplify the schema of the database. Extensive experiments through 5-fold cross-validation on the NVBench dataset demonstrate the superiority of Prompt4Vis, which notably surpasses the state-of-the-art (SOTA) RGVisNet by approximately 35.9% and 71.3% on dev and test sets, respectively. To the best of our knowledge, Prompt4Vis is the first work that introduces in-context learning into the text-to-vis for generating data visualization queries.

Zhuoqun Li, Haiyang Yu, Xuanang Chen et al.

Designing solutions for complex engineering challenges is crucial in human production activities. However, previous research in the retrieval-augmented generation (RAG) field has not sufficiently addressed tasks related to the design of complex engineering solutions. To fill this gap, we introduce a new benchmark, SolutionBench, to evaluate a system's ability to generate complete and feasible solutions for engineering problems with multiple complex constraints. To further advance the design of complex engineering solutions, we propose a novel system, SolutionRAG, that leverages the tree-based exploration and bi-point thinking mechanism to generate reliable solutions. Extensive experimental results demonstrate that SolutionRAG achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications.

Shiwen Ni, Guhong Chen, Shuaimin Li et al.

In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in increasing numbers. As a quantitative assessment tool for model performance, benchmarks are not only a core means to measure model capabilities but also a key element in guiding the direction of model development and promoting technological innovation. We systematically review the current status and development of large language model benchmarks for the first time, categorizing 283 representative benchmarks into three categories: general capabilities, domain-specific, and target-specific. General capability benchmarks cover aspects such as core linguistics, knowledge, and reasoning; domain-specific benchmarks focus on fields like natural sciences, humanities and social sciences, and engineering technology; target-specific benchmarks pay attention to risks, reliability, agents, etc. We point out that current benchmarks have problems such as inflated scores caused by data contamination, unfair evaluation due to cultural and linguistic biases, and lack of evaluation on process credibility and dynamic environments, and provide a referable design paradigm for future benchmark innovation.

Xuanang Chen, Ben He, Zheng Ye et al.

Adversarial attacks have gained traction in order to identify potential vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce grammatical errors, nonsensical expressions, or incoherent text fragments, which can be easily detected. Additionally, current methods rely heavily on the use of a well-imitated surrogate NRM to guarantee the attack effect, which makes them difficult to use in practice. To address these issues, we propose a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents that are less noticeable to both algorithms and humans. IDEM instructs a well-established generative language model, such as BART, to generate connection sentences without introducing easy-to-detect errors, and employs a separate position-wise merging strategy to balance relevance and coherence of the perturbed text. Experimental results on the popular MS MARCO benchmark demonstrate that IDEM can outperform strong baselines while preserving fluency and correctness of the target documents as evidenced by automatic and human evaluations. Furthermore, the separation of adversarial text generation from the surrogate NRM makes IDEM more robust and less affected by the quality of the surrogate NRM.

Xuanang Chen, Ben He, Kai Hui et al.

Despite the effectiveness of utilizing the BERT model for document ranking, the high computational cost of such approaches limits their uses. To this end, this paper first empirically investigates the effectiveness of two knowledge distillation models on the document ranking task. In addition, on top of the recently proposed TinyBERT model, two simplifications are proposed. Evaluations on two different and widely-used benchmarks demonstrate that Simplified TinyBERT with the proposed simplifications not only boosts TinyBERT, but also significantly outperforms BERT-Base when providing 15$\times$ speedup.