论文检索

Jonggwon Park, Byungmu Yoon, Soobum Kim, Kyoyun Choi

Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large language models (MLLMs) have enabled multimodal chest X-ray (CXR) report generation. However, existing MLLMs are computationally expensive, require large-scale training data, and may produce hallucinated content, limiting their practical deployment. To address these limitations, we propose RA-RRG, a retrieval-augmented RRG framework that combines multimodal retrieval with large language models (LLMs) to generate radiology reports while reducing hallucinations and computational demands. RA-RRG uses LLMs to extract clinically essential key phrases from radiology reports and retrieves relevant phrases given an input image. By conditioning LLMs on the retrieved phrases, RA-RRG effectively suppresses hallucinations while maintaining strong report generation performance. Experiments on the MIMIC-CXR and IU X-ray datasets show state-of-the-art results on CheXbert metrics and competitive RadGraph F1 scores compared to MLLMs. Furthermore, RA-RRG naturally generalizes to multi-view RRG by aggregating phrases retrieved from multiple images, highlighting its broad applicability to real-world clinical scenarios. Code is available at https://github.com/deepnoid-ai/RA-RRG.

Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools via protocols such as the Model Context Protocol (MCP) introduces critical security vulnerabilities, including prompt injection, data exfiltration, and other threats. To counter these challenges, we propose MCP-Guard, a robust, layered defense architecture designed for LLM–tool interactions. MCP-Guard employs a three-stage detection pipeline that balances efficiency with accuracy: it progresses from lightweight static scanning for overt threats and a deep neural detector for semantic attacks, to our fine-tuned E5-based model achieves 96.01% accuracy in identifying adversarial prompts. Finally, an LLM arbitrator synthesizes these signals to deliver the final decision. To enable rigorous training and evaluation, we introduce MCP-AttackBench, a comprehensive benchmark comprising 70,448 samples augmented by GPT-4. This benchmark simulates diverse real-world attack vectors that circumvent conventional defenses in the MCP paradigm, thereby laying a solid foundation for future research on securing LLM-tool ecosystems.

H S V N S Kowndinya Renduchintala, Sumit Bhatia

Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence: while they learn some linguistic phenomena with near-perfect mastery, they often perform below chance on others, even after training on trillions of tokens. In this work, we investigate whether these failures stem from inherent architectural limitations or simply the scarcity of these specific grammatical constructions in web-scale corpora. We pre-train simple GPT-2 Small (124M) models on a 100M-token random sample of the FineWeb corpus and intervene by injecting a minimal amount (1%) of synthetic data targeting specific linguistic phenomena. We find that this targeted intervention substantially improves model performance in 8 out of the 9 worst-performing BLiMP paradigms – notably the accuracy on a specific paradigm, only_npi_scope, surges from 20.9% to 69.4%. Furthermore, we observe that these interventions generally preserve or slightly improve aggregate performance. However, while we also identify a resistant phenomenon, principle_A_c_command, whose performance remains below chance even after our data augmentation, our findings do serve as an optimistic existence proof that even small language models can substantially improve on those linguistic phenomena on which models typically perform poorly, provided the pre-training data contains sufficient exposure to them. This suggests that efforts towards human-scale language modeling may benefit greatly by focusing on data composition. The code to reproduce our results is open-sourced at https://github.com/kowndinya-renduchintala/heterogeneity-in-formal-linguistic-competence.

Yuanze Hu, Xinyu Wang, Zhichao Yang, Gen Li, Ye Qiu, Zhaoxin Fan, Yifan Sun, Wenjun wu, Jin Dong, Xiaotie Deng

Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing both the vision encoder and the language model while training small connector modules. However, this strategy heavily depends on the intrinsic capabilities of the language model, which can be suboptimal for lightweight models with limited representational capacity. In this work, we investigate this alignment bottleneck through the lens of mutual information, positing that the constrained capacity of the language model inherently limits the Effective Mutual Information (EMI) between multimodal inputs and outputs, thereby compromising alignment quality. To address this challenge, we propose TinyAlign, a novel framework inspired by Retrieval-Augmented Generation, which strategically retrieves relevant context from a memory bank constructed from training data to enrich multimodal inputs and enhance their alignment. Extensive empirical evaluations reveal that TinyAlign significantly reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead. Remarkably, it allows models to achieve baseline-level performance with only 40% of the fine-tuning data, highlighting exceptional data efficiency. Our work thus offers a practical pathway for developing more capable lightweight VLMs while introducing a fresh theoretical lens to better understand and address alignment bottlenecks in constrained multimodal systems.

Qianyu Wang, Xiaoman Wang, Yuanyuan Liang, Xinyuan Li, Yunshi Lan

Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates that the existing GEC models usually fail to understand the error patterns in the varying contexts. In this paper, we thoroughly investigate the counterfactuals for GEC tasks, where the subtle changes to the contexts could lead to the label flipping issue. We address this robustness gap by viewing contextual variation through the lens of counterfactual data. We propose CoCoGEC, a counterfactual generation framework that creates copies of training instances with error-irrelevant contexts altered. Our framework systematically generates counterfactuals by (1) generating intra- and inter-sentence counterfactuals that maintain the error patterns as well as syntax of the original instances by altering the word-level and sentence-level contexts; (2) revising the generated counterfactuals by selecting the instances with flipped labels and high GEC Mutual Information (MI) coefficient. Extensive experiments show that our method substantially improves the stability of GEC models, outperforming a set of data augmentation baselines. Particularly, it could achieve absolute F_{0.5} gains of +9.9, +11.3, and +20.8 points on the perturbed BEA-19*,CoNLL-14*, and TEM-8* data set.Our code is released at https://github.com/Quinnok/CoCoGEC.

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang 等

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for realistic financial analysis over financial documents. However, existing benchmarks fail to capture realistic financial analysis settings that involve cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. To address this gap, we introduce \textbf{FinMRAGBench}, a comprehensive multi-modal financial RAG benchmark in which most questions require retrieving evidence scattered across multiple pages and documents, constructed from large-scale real-world annual reports and comprising 887 expert-verified QA pairs spanning five representative financial analysis tasks. Moreover, we introduce \textbf{FinMRAGAgent}, an agent trained on high-quality agentic trajectories following the reasoning-and-acting (ReAct) paradigm, capable of dynamic tool invocation and multi-step financial analysis. Our extensive experiments show that current multi-modal RAG systems still struggle with incomplete retrieval and complex financial reasoning. In contrast, FinMRAGAgent achieves the strongest overall performance across all models, demonstrating that our structured reasoning approach significantly enhances multi-modal RAG in realistic financial scenarios. The code and data are available at https://github.com/sqyangit/FinMRAGBench.

Chengxi She, Zhiqiang Chen, Xingyu Lu, Caihua Chen, Piaoyang Zhao, Xuedong Wang

To address two correlated question in Optimization under Uncertainty (OuU): Expertise Threshold and Selection Conundrum, we propose LLM4OuU, a multi-agent framework that automates both the modeling and solving of six distinct types of uncertainty models and generates mapping pairs to explore the potential relationship between optimization problems and optimal models. Firstly, we decompose the complex modeling process into five sequential steps and design specialized LLM agents combining high-level domain expertise. Secondly, we introduce a hybrid dataset spanning various industries based on Retrieval-Augmented Generation (RAG) to benchmark performance. Extensive experiments demonstrate that LLM4OuU achieves superior performance compared to baselines, even reaching up to 99% on specific model types. Finally, we establish a mapping from problem features to optimal models, with correlation analysis revealing that not only data scale but also the specific scenario significantly influence model selection.

Hongjin Qian, Siqi Bao, Zhao Cao, Zheng Liu

Information seeking bridges the knowledge gap between a query and its answer. Although LLMs perform well broadly, their ability to close this gap is limited by pretraining and degrades on specialized or up-to-date queries. A common remedy augments LLMs with external knowledge, either by injecting retrieved evidence into context or interleaving retrieval with reasoning. The former limits exploration of layered dependencies, while the latter is bounded by context length, constraining efficiency and scalability. For complex tasks with intricate dependencies and large text volumes, both approaches become inadequate.To tackle this bottleneck, we present AWARE (Agentic Knowledge Warehouse), an agentic knowledge warehousing framework that transforms heterogeneous, unstructured data into minimal, task-conditioned knowledge representations consumable by LLMs. Rather than exposing raw text, AWARE constructs knowledge through intent planning, online multi-threaded exploration, and map-reduce evidence integration, producing compact, LLM-ready context under finite budgets. Specifically, it applies offline document structuring to generate document headers that support controlled access, performs exploration with targeted refinement to recover layered information dependencies, and integrates distributed evidence into task-aware representations for downstream answer generation. Experiments on GAIA, WebWalker, and BrowseComp-Plus show improvements over all baselines

Soyeong Jeong, Taehee Jung, Sung Ju Hwang, Joo-Kyung Kim, Dongyeop Kang

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, reusable reasoning patterns derived from prior problem solving that structure how evidence is combined and guide multi-hop inference alongside factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into relatively smaller open-source models, demonstrating its broad applicability. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).

Jingwen Deng, Jihao Huang, Zhen Hao Wong, Hao Liang, Quanqing Xu, Bin Cui, Wentao Zhang

Large Language Models (LLMs) excel at natural language understanding and generation, yet their reliance on static pre-training corpora may lead to outdated knowledge, hallucinations, and limited adaptability. Retrieval-Augmented Generation (RAG) mitigates these issues by grounding model outputs with external retrieval, but conventional RAG remains constrained by a fixed retrieve-then-generate routine and struggles with multi-step reasoning and tool calls. **Agentic RAG** addresses these limitations by enabling LLM agents to actively decompose tasks, issue exploratory queries, and refine evidence through iterative retrieval. Despite growing interest, the development of Agentic RAG is impeded by *data scarcity*: unlike traditional RAG, it requires challenging tasks that require planning, retrieval, and multiple reasoning decisions, and corresponding rich, interactive agent trajectories. This survey presents the first data-centric overview of Agentic RAG, framing its data lifecycle—data collecting, data preprocessing and task formulation, task construction, data for evaluation, and data enhancement for training—and cataloging representative training datasets and benchmarks in different domains (e.g. question answering, web, software engineering). From data perspectives, we aim to guide the creation of scalable, high-quality datasets for the next generation of adaptive, knowledge-seeking LLM agents. The project page is at https://github.com/fatty-belly/Awesome-AgenticRAG-Data/.

Haoran Sun, Zekun Zhang, Shaoning Zeng

The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference optimization, improve user alignment yet fail to enhance the model’s domain cognition. To bridge this gap, we propose a novel Dual-Phase Self-Evolution (DPSE) framework that jointly optimizes user preference adaptation and domain-specific competence. DPSE introduces a Censor module to extract multi-dimensional interaction signals and estimate satisfaction scores, which guide structured data expansion via topic-aware and preference-driven strategies. These expanded datasets support a two-stage fine-tuning pipeline: supervised domain grounding followed by frequency-aware preference optimization. Experiments across general NLP benchmarks and long-term dialogue tasks demonstrate that DPSE consistently outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines. Ablation studies validate the contribution of each module. In this way, our framework provides an autonomous path toward continual self-evolution of LLMs.

Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye 等

Large Language Models (LLMs) have demonstrated strong mathematical reasoning abilities through supervised fine-tuning and reinforcement learning. However, existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps, limiting their reliability and scalability. To address the first problem, we propose a novel reward model approach, Hierarchical Reward Model (HRM), which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grained level. HRM excels at assessing multi-step mathematical reasoning coherence, particularly in cases where a flawed step is later corrected through self-reflection. Furthermore, to address the inefficiency of autonomously annotating PRM training data via Monte Carlo Tree Search (MCTS), we propose a lightweight data augmentation strategy, Hierarchical Node Compression (HNC), which merges consecutive reasoning steps within the tree structure. Applying HNC to MCTS-generated reasoning trajectories increases the diversity and robustness of HRM training data, while introducing controlled noise with minimal computational overhead. Empirical results on the PRM800K dataset demonstrate that HRM, in conjunction with HNC, achieves superior stability and reliability in evaluation compared to PRM. Furthermore, cross-domain evaluations on MATH500 and GSM8K dataset confirm HRM’s superior generalization and robustness across diverse mathematical reasoning tasks.

Hang Lv, Hongchao Gu, Ruiqing Yang, Liangyue Li, Zulong Chen, Defu Lian, Hao Wang, Enhong Chen

Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order independent of relevance. Existing mitigations present a dilemma: inference-time aggregation incurs prohibitive latency, while training-based methods often fail to eradicate ingrained priors, particularly in compact models. To resolve this dilemma, we propose CapCal (Content-Agnostic Probability Calibration), a training-free framework that mechanically decouples positional bias from ranking decisions. By estimating the bias distribution via content-free placeholders, CapCal rectifies output logits through an entropy-adaptive contrastive mechanism. Evaluations across 10 benchmarks confirm that CapCal achieves superior performance among training-free methods while preserving single-pass efficiency. Notably, it unlocks the latent potential of lightweight models (e.g., 0.6B), delivering absolute NDCG gains exceeding 10 points and outperforming computationally expensive data augmentation strategies.

Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, Sattvik Sahai, Prasoon Goyal, Kai-Wei Chang, Tao Zhang, Rahul Gupta

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such cross-domain generalization of harmful behavior underscores the need for a deeper understanding of the algorithms, tasks, and datasets that induce emergent misalignment. In this work, we extend this study by demonstrating that emergent misalignment can also arise from narrow refusal unlearning in specific domains. We perform refusal unlearning on Cybersecurity and Safety concept, and evaluate EMA by monitoring refusal scores across seven responsible AI (RAI) domains, Cybersecurity, Safety, Toxicity, Bias, Sensitive Content, Medical/Legal, and Privacy. Our work shows that narrow domain unlearning can yield compliance responses for the targeted concept, however, it may also propagate EMA to unrelated domains. Among the two intervened concepts, Cybersecurity and Safety, we find that the safety concept can have larger EMA impact, i.e, causing lower refusal scores, across other unrelated domains such as bias. We observe this effect consistently across two model families, Mistral-7b-0.3v, and Qwen-7b-2.5. Further, we show that refusal unlearning augmented with cross-entropy loss function on a small set of retain data from the affected domains can largely, if not fully, restore alignment across the impacted domains while having lower refusal rate on the concept we perform unlearning on. To investigate the underlying causes of EMA, we analyze concept entanglements at the representation level via concept vectors. Our analysis reveals that concepts with higher representation similarity in earlier layers are more susceptible to EMA after intervention when the refusal stream is altered through targeted refusal unlearning.

Yiwei Qin, Zhen Huang, Tiantian Mi, Weiye Si, Qipeng Guo, Siyuan Feng, Pengfei Liu

High-quality scientific data is critical for advancing LLMs, yet academic literature remains largely underutilized. This work addresses the fundamental question: How can we systematically unlock scientific data’s value for pre-training? First, we construct a large-scale raw scientific corpus but identify a critical Learnability Gap, revealing that direct pre-training yields negligible gains. To bridge this, we develop a multi-stage pipeline featuring content cleaning and pedagogical augmentation, resulting in SciPedia, a 900B-token corpus. Finally, we establish a controlled verification framework: we develop SciPedia-Eval benchmark and conduct 600B tokens of continued pre-training (CPT) starting from transparent base models (3B/7B) trained from scratch. Compared to a CPT baseline trained with general-purpose data, our approach with SciPedia data boosts average performance by +2.12 (3B) and +2.95 (7B), reaching +5.60 and +8.40 on in-domain tasks. This setup further allows us to derive empirical guidelines for data composition and model configurations.

Deepak Kumar, Baban Gain, Asif Ekbal

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed, such disfluencies can significantly degrade the reliability of downstream systems. Most existing approaches rely on classical models that focus on identifying disfluent tokens for removal. While this strategy is effective to some extent, it often disrupts grammatical structure and semantic coherence, leading to incomplete or unnatural sentences. Recent literature explored the use of large language models (LLMs); however, these efforts have primarily focused on disfluency detection or data augmentation, rather than performing comprehensive correction. We propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning of an LLM to rewrite transcripts into fluent text. To further improve reliability, we add a contrastive learning objective that penalizes the reproduction of disfluent tokens, encouraging the model to preserve grammar and meaning while removing disfluent artifacts. Our experiments across three Indian languages, namely Hindi, Bengali, and Marathi show consistent improvements over strong baselines, including multilingual sequence-to-sequence models. These results highlight that detection-only strategies are insufficient. Combining token-level cues with instruction tuning and contrastive learning provides a practical and scalable solution for multilingual disfluency correction in speech-driven NLP systems. We make the codes publicly available at https://github.com/deepak-kumar-98/Mind-the-Pause.

Lingdi Kong, Xuanang Chen, Ben He, Le Sun

Dense retrieval has become a core technique in applications like web search and retrieval-augmented generation. Despite their empirical success, it remains unclear whether these models truly understand semantics. To address this gap, this paper conducts a systematic investigation by introducing SURE, a benchmark for Semantic Understanding in dense REtrieval built upon the MSMARCO, NQ, and FiQA datasets. SURE characterizes semantic understanding in dense retrieval along three dimensions: semantic precision, semantic abstraction, and semantic equivalence. We evaluate ten representative models ranging from 110M to 8B parameters, including both general-purpose and domain-specific models. Results show that current dense retrievers struggle to distinguish fine-grained semantic differences across texts with varying information density, and to recognize semantic consistency under lexical paraphrasing. Moreover, larger models do not necessarily exhibit stronger semantic understanding, and diverse training data generally enhances semantic understanding on challenging retrieval tasks.

Bruno Gatti, Giuliano Martinelli, Roberto Navigli

Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted and gold clusters. While widely used, these metrics offer limited diagnostic insights, penalizing errors without revealing whether a system struggles with specific semantic categories, such as people, locations, or events, and making it difficult to interpret model capabilities or derive actionable improvements. We address this gap by introducing a semantically-enhanced evaluation framework for coreference resolution. Our approach overlays Concept and Named Entity Recognition (CNER) onto coreference outputs, assigning semantic labels to nominal mentions and propagating them to entire coreference clusters. This enables the computation of typed scores aimed at evaluating mention extraction and linking capabilities stratified by semantic class. Across our experiments on OntoNotes, LitBank, and PreCo, we show that our framework uncovers systematic weaknesses that remain obscured by aggregate metrics. Furthermore, we show that these diagnostics can be used to design targeted, low-cost data augmentation strategies, achieving measurable out-of-domain improvements.

Weixin Chen, Yuhan Zhao, Jingyuan Huang, Zihe Ye, Mingxuan Ju, Tong Zhao, Neil Shah, Li Chen, Yongfeng Zhang

The evolution of recommender systems has shifted from traditional collaborative filtering to LLM-based agentic systems, which rely on semantic user and item memories to make predictions. However, existing agents maintain these memories in isolation. This overlooks crucial collaborative signals, such as user-item co-engagements and peer relationships across the community, which significantly limits their ability to uncover hidden preferences and accurately infer user needs, particularly for data-sparse users. To bridge this gap, we introduce collaborative memory, a paradigm that connects isolated semantics to enable the sharing of relational insights. Yet, naively utilizing collaborative memory causes severe context overload and introduces noise to downstream LLMs, alongside prohibitive computational costs. To resolve this, we propose MemRec, a framework that architecturally decouples memory management from reasoning. MemRec introduces a dedicated, lightweight language model LM_Mem to efficiently manage and synthesize a dynamic collaborative memory graph in the background. It provides only distilled, high-signal contexts to a downstream, heavyweight large language model (LLM_Rec) for the final recommendation. Extensive experiments on four benchmarks demonstrate that MemRec achieves state-of-the-art performance. Code: https://github.com/rutgerswiselab/memrecHomepage: https://memrec.weixinchen.com

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang

Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human’s behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs’ ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models’ performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark and dataset for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.