Retrieval-augmented generation (RAG) is an effective approach to enhancing the factual accuracy of radiology reports. However, existing methods primarily model coarse-grained image–report correspondences, ignoring semantic relations among reports that capture hierarchical and fine-grained pathological knowledge. As a result, the learned representations fail to reflect detailed clinical semantics, causing factual inconsistencies in generated reports. Therefore, we propose a multi-granularity knowledge-integrated RAG framework for radiology reports. Specifically, we utilize multi-granularity semantic similarities, derived from the text modality, to adjust the original cross-modal contrastive learning loss. This guides the multimodal retriever to learn a finer-grained clinical semantic alignment. Then, we utilize cross attention to obtain enhanced visual features by integrating the retrieved reports with the original images, thus enhancing the factual accuracy of report generation. The effectiveness of our method was verified on two widely used benchmarks, achieving superior performance in both language generation and key clinical metrics.
论文检索
输入标题、作者或关键词，从 1,386 篇学术成果中精准定位
Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory—particularly in complex, long-term Web-based services such as online emotional support. However, existing long-term dialogue benchmarks primarily focus on static and explicit fact retrieval, failing to evaluate agents in these critical scenarios where user information is dispersed, implicit, and continuously evolving. To address this gap, we introduce ES-MemEval, a comprehensive benchmark that systematically evaluates five core memory capabilities—information extraction, temporal reasoning, conflict detection, abstention, and user modeling—in long-term emotional support scenarios, covering question answering, summarization, and dialogue generation tasks. To support the benchmark, we also propose EvoEmo, the first multi-session dataset for personalized long-term emotional support scenarios, capturing fragmented, implicit user disclosures and evolving user states. Extensive experiments on open-source long-context, commercial, and retrieval-augmented (RAG) LLMs reveal that explicit long-term memory is essential to reduce hallucinations and enable effective personalization. At the same time, RAG enhances factual consistency but struggles with temporal dynamics and evolving user states. These findings highlight both the potential and limitations of current paradigms, encouraging the development of more robust memory–retrieval integration in long-term personalized dialogue systems.
Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by the vision of continuous knowledge acquisition in NELL and fueled by advances in LLM-based agents, this paper introduces WINEL, an agentic framework for continuously updating Wikipedia articles. Our approach employs a multi-agent framework to aggregate online information, select new and important knowledge for a target entity in Wikipedia, and then generate precise edit suggestions for human review. Our fine-grained editing models, trained on Wikipedia's extensive history of human edits, enable incorporating updates in a manner consistent with human editing behavior. Our editor models outperform both open-source instruction-following baselines and closed-source LLMs (e.g., GPT-4o) in key-information coverage and editing efficiency. End-to-end evaluation on high-activity Wikipedia pages demonstrates WINELL's ability to identify timely factual updates. This opens up a promising research direction in LLM agents for automatically updating knowledge bases in a never-ending fashion.
Large Language Models (LLMs) have shown remarkable performance on general Question Answering (QA), yet they often struggle in domain-specific scenarios where accurate and up-to-date information is required. Retrieval-Augmented Generation (RAG) addresses this limitation by enriching LLMs with external knowledge, but existing systems primarily rely on unstructured documents, while largely overlooking relational databases, which provide precise, timely, and efficiently queryable factual information, serving as indispensable infrastructure in domains such as finance, healthcare, and scientific research. Motivated by this gap, we conduct a systematic analysis that reveals three central observations: (i) databases and documents offer complementary strengths across queries, (ii) naively combining both sources introduces noise and cost without consistent accuracy gains, and (iii) selecting the most suitable source for each query is crucial to balance effectiveness and efficiency. We further observe that query types show consistent regularities in their alignment with retrieval paths, suggesting that routing decisions can be effectively guided by systematic rules that capture these patterns. Building on these insights, we propose a rule-driven routing framework designed specifically for hybrid-source RAG. A routing agent scores candidate augmentation paths based on explicit rules and selects the most suitable one; a rule-making expert agent refines the rules using QA feedback to produce more comprehensive and reliable decision criteria; and a path-level meta-cache reuses past routing decisions for semantically similar queries to reduce latency and cost. Experiments on three QA datasets demonstrate that our framework consistently outperforms static strategies and learned routing baselines, achieving higher accuracy while maintaining moderate computational cost.
Large Language Models (LLMs) inevitably encounter factual hallucinations and knowledge obsolescence, necessitating lifelong knowledge editing to sustain reliability and factual advancement. While mainstream lifelong editing paradigms aim to alleviate knowledge forgetting through allocating and updating isolated parameter subspaces, they often overlook conflict assessment among distinct editing processes, leading to unjustified subspace allocation and indiscriminate neuron tuning. To address these issues, we propose the Conflict-Assessed Sensitive Editing (CASE) framework, which integrates a Conflict-Assessed Editing Allocation (CAA) module and a Knowledge-sensitive Neuron Tuning (KNT) strategy. The CAA module quantitatively assesses editing conflicts to enable justified subspace allocation, thereby reducing globally significant conflicts and routing errors. The KNT strategy adaptively identifies and tunes knowledge-sensitive neurons through a calibrated sensitivity threshold, effectively eliminating local conflicts and enhancing subspace stability. Extensive experiments on standard lifelong editing benchmarks demonstrate that CASE achieves state-of-the-art performance, improving average editing accuracy by nearly 10% after 1,000 sequential edits. Overall, CASE substantially mitigates editing conflicts and enhances knowledge retention, offering a scalable and conflict-resilient solution for lifelong model editing.
Retrieval-augmented generation (RAG) has proven effective at mitigating limitations of large language models (LLMs), including outdated knowledge, semantic gaps, and hallucinations. However, existing RAG techniques are primarily optimised for factual question answering—where answers can be directly retrieved—rather than for predictive tasks that require inferring unknown outcomes, such as user preferences in recommendations. To address this gap, we propose PRAG, a RAG framework tailored for predictive settings. PRAG computes the semantic similarity between a user's historical interactions and target information, and adaptively integrates this similarity as prompt weights, thereby enhancing the LLM's ability to model personalised, semantics-informed preferences. PRAG integrates seamlessly into LLM-based applications; instantiated in recommender systems, it explicitly captures user-specific preference signals via semantic similarity modelling. Experiments using two LLM backbones and four real-world datasets show that PRAG significantly improves predictive recommendation performance.
Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs) to perform more precise and explainable reasoning. While KG-RAG improves factual accuracy in complex tasks, existing KG-RAG models are often severely overconfident, producing high-confidence predictions even when retrieved sub-graphs are incomplete or unreliable, which raises concerns for deployment in high-stakes domains. To address this issue, we propose Ca2KG, a Causality-aware Calibration framework for KG-RAG. Ca2KG integrates counterfactual prompting, which exposes retrieval-dependent uncertainties in knowledge quality and reasoning reliability, with a panel-based re-scoring mechanism that stabilises predictions across interventions. Extensive experiments on two complex QA datasets demonstrate that Ca2KG consistently improves calibration while maintaining or even enhancing predictive accuracy. The source code can be found at~ https://aisuko.github.io/ca2kg/.
Knowledge Graph Question Answering (KGQA) aims to answer natural language questions by reasoning over structured knowledge graphs (KGs). While large language models (LLMs) have advanced KGQA through their strong reasoning capabilities, existing methods continue to struggle to fully exploit both the rich knowledge encoded in KGs and the reasoning capabilities of LLMs, particularly in complex scenarios. They often assume complete KG coverage and lack mechanisms to judge when external information is needed, and their reasoning remains locally myopic, failing to maintain coherent multi-step planning, leading to reasoning failures even when relevant knowledge exists. We propose Graph-RFT, a novel two-stage reinforcement fine-tuning KGQA framework with a ''plan–KGsearch–and–Websearch–during–think'' paradigm, that enables LLMs to perform autonomous planning and adaptive retrieval scheduling across KG and web sources under incomplete knowledge conditions. Graph-RFT introduces a chain-of-thought (CoT) fine-tuning method with a customized plan–retrieval dataset activates structured reasoning and resolves the GRPO cold-start problem. It then introduces a novel plan–retrieval guided reinforcement learning process integrates explicit planning and retrieval actions with a multi-reward design, enabling coverage-aware retrieval scheduling. It employs a Cartesian-inspired planning module to decompose complex questions into ordered sub-questions, and logical expression to guide tool invocation for globally consistent multi-step reasoning. This reasoning–retrieval process is optimized with a multi-reward combining outcome and retrieval-specific signals, enabling the model to learn when and how to combine KG and web retrieval effectively. Experiments on multiple KGQA benchmarks demonstrate that Graph-RFT achieves superior performance over strong baselines, even with smaller LLM backbones, and substantially improves complex question decomposition, factual coverage, and tool coordination.
Large Language Models (LLMs), as common components of modern web application backends and online services, are being widely deployed across various web infrastructures in the .gguf single-file format. This trend exposes their model parameter space to an unprecedented hardware attack surface, such as Bit-Flip attacks (BFA). This paper is the first to systematically discover and validate the existence of single-bit vulnerabilities in LLMs weight files: In the .gguf quantization format of mainstream open-source models (such as DeepSeek, QWEN), flipping a single bit can induce three types of targeted semantic-level faults, respectively-Artificial Flawed Intelligence (outputting factual errors), Artificial Weak Intelligence (catastrophic model failure), and Artificial Bad Intelligence (generating harmful content). By building an information-theoretic weight sensitivity entropy model and a probabilistic heuristic scanning framework called BitSifter, we achieved efficient localization of critical vulnerable bits in models with hundreds of millions of parameters. Furthermore, an end-to-end remote BFA chain was designed, enabling semantic-level attacks in real-world web server deployment scenarios: At an attack frequency of 464.3 times per second, the average time required for the first successful flip of the target bit is 31.7 seconds, without requiring high-cost equipment or complex prompt engineering. This study reveals a critical finding: under relatively modest remote-attack conditions, requiring only conventional network connectivity, flipping a single vulnerable bit within the tensor data segment can cause models deployed in web service environments to autonomously generate extremely malicious responses, such as ''humans should be exterminated'', or produce naturally fluent and difficult-to-detect erroneous replies to ordinary user queries. This demonstrates a pervasive and exploitable security vulnerability in LLMs systems at the fundamental hardware level.
Graph-based Retrieval-Augmented Generation (RAG) typically operates on binary Knowledge Graphs (KGs). However, decomposing complex facts into binary triples often leads to semantic fragmentation and longer reasoning paths, increasing the risk of retrieval drift and computational overhead. In contrast, n-ary hypergraphs preserve high-order relational integrity, enabling shallower and more semantically cohesive inference. To exploit this topology, we propose HyperRAG, a framework tailored for n-ary hypergraphs featuring two complementary retrieval paradigms: (i) HyperRetriever learns structural-semantic reasoning over n-ary facts to construct query-conditioned relational chains. It enables accurate factual tracking, adaptive high-order traversal, and interpretable multi-hop reasoning under context constraints. (ii) HyperMemory leverages the LLM's parametric memory to guide beam search, dynamically scoring n-ary facts and entities for query-aware path expansion. Extensive evaluations on WikiTopics (11 closed-domain datasets) and three open-domain QA benchmarks (HotpotQA, MuSiQue, and 2WikiMultiHopQA) validate HyperRAG's effectiveness. HyperRetriever achieves the highest answer accuracy overall, with average gains of 2.95% in MRR and 1.23% in Hits@10 over the strongest baseline. Qualitative analysis further shows that HyperRetriever bridges reasoning gaps through adaptive and interpretable n-ary chain construction, benefiting both open and closed-domain QA. Our codes are publicly available at https://github.com/Vincent-Lien/HyperRAG.git.
Large Language Models (LLMs) have demonstrated strong capabilities in web search and reasoning. However, their dependence on static training corpora makes them prone to factual errors and knowledge gaps. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge sources, especially structured Knowledge Graphs (KGs), which provide explicit semantics and efficient retrieval. Existing KG-based RAG approaches, however, generally assume that anchor entities are accessible to initiate graph traversal, which limits their robustness in open-world settings where accurate linking between the user query and the KG entity is unreliable. To overcome this limitation, we propose AnchorRAG, a novel multi-agent collaboration framework for open-world RAG without the predefined anchor entities. Specifically, a predictor agent dynamically identifies candidate anchor entities by aligning user query terms with KG nodes and initializes independent retriever agents to conduct parallel multi-hop explorations from each candidate. Then a supervisor agent formulates the iterative retrieval strategy for these retriever agents and synthesizes the resulting knowledge paths to generate the final answer. This multi-agent collaboration framework improves retrieval robustness and mitigates the impact of ambiguous or erroneous anchors. Extensive experiments on four public benchmarks demonstrate that AnchorRAG significantly outperforms existing baselines and establishes new state-of-the-art results on the real-world reasoning tasks.
The rapid spread of misinformation on social media has underscored the importance of automatic fact-checking. Existing fact-checking pipelines typically rely on multi-stage frameworks involving evidence retrieval and claim verification. However, these methods face two major challenges: (1) the retrieval process often introduces noisy evidence, which compromises the reliability of the final veracity prediction; and (2) the verification models may overlook critical factual details, resulting in hallucinated conclusions. To address these issues, we propose a fact-checking framework SLED with Self-supervised denoising evidence retrieval and LLM-Enhanced Debate-based verification. In the retrieval stage, SLED leverage trained verifier to assess credibility and necessity of retrieved evidence, enabling the elimination of noisy evidence. In the verification stage, SLED prompts the LLM to generate dual-perspective reasoning and simulates a multi-agent debate, followed by distillation into a lightweight model for final veracity prediction. Experiments on CHEF and HOVER datasets demonstrate that SLED achieves the state-of-the-art results in complex fact verification scenarios.
Retrieval is being redefined by agentic AI, demanding multimodal reasoning beyond conventional similarity-based paradigms. Composed Image Retrieval (CIR) exemplifies this shift as each query combines a reference image with textual modifications, requiring compositional understanding across modalities. While embedding-based CIR methods have achieved progress, they remain narrow in perspective, capturing limited cross-modal cues and lacking semantic reasoning. To address these limitations, we introduce XR, a training-free multi-agent framework that reframes retrieval as a progressively coordinated reasoning process. It orchestrates three specialized types of agents: imagination agents synthesize target representations through cross-modal generation, similarity agents perform coarse filtering via hybrid matching, and question agents verify factual consistency through targeted reasoning for fine filtering. Through progressive multi-agent coordination, XR iteratively refines retrieval to meet both semantic and visual query constraints, achieving up to a 38% gain over strong training-free and training-based baselines on FashionIQ, CIRR, and CIRCO, while ablations show each agent is essential. Code is available: https://01yzzyu.github.io/xr.github.io/.
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive searches as they cannot accurately judge when to stop searching and start answering. This stems from outcome-centric training that prioritize final results over the search process itself. We identify the root cause as misaligned decision boundaries, the threshold determining when accumulated information suffices to answer. This causes over-search (redundant searching despite sufficient knowledge) and under-search (premature termination yielding incorrect answers). To address these errors, we propose a comprehensive framework comprising two key components. First, we introduce causal intervention-based diagnosis that identifies boundary errors by comparing factual and counterfactual trajectories at each decision point. Second, we develop Decision Boundary Alignment for Deep Search agents (DAS), which constructs preference datasets from causal feedback and aligns policies via preference optimization. Experiments on public datasets demonstrate that decision boundary errors are pervasive across state-of-the-art agents. Our DAS method effectively calibrates these boundaries, mitigating both over-search and under-search to achieve substantial gains in accuracy and efficiency. Our code and data are publicly available at: https://github.com/Applied-Machine-Learning-Lab/WWW2026_DAS.
Retrieval-augmented generation (RAG) has become a cornerstone for enhancing large language models (LLMs) with real-time information from the Web, but its performance often heavily depends on the quality of the retrieved documents. Given that RAG systems frequently draw from vast and often noisy Web corpora, ensuring the reliability of retrieved content is paramount. While rerankers improve the factual accuracy of the RAG system by elevating the proportion of ground-truth documents (GD) in high-ranked results, the shifts of document type distributions during reranking remain unclear, hindering the understanding of the reranker's behavior. To bridge this gap, we conduct an empirical study to categorize documents and compare their distribution before and after reranking. We reveal a counterintuitive finding: though rerankers improve the proportion of GD, they also significantly increase the proportion of harmful documents (HD) in top-ranked retrieved documents. It not only narrows the potential context window for ranking the GD higher but also increases the risk of HD misleading the LLMs, potentially leading to the generation and propagation of misinformation across Web platforms. Motivated by this finding, we propose a risk-aware reranking method for RAG with LLMs, which balances the risk and benefit during reranking. Given a query, the RAG framework first retrieves relevant documents. Then, our approach quantifies the potential beneficial and harmful impacts of various documents on the LLMs' generation. To estimate the impacts, we conduct a dual-aspect document impact assessment via information gain, which employs a risk clipping to avoid the numerical fluctuations in the estimation. Finally, we conduct the reranking according to the potential impact of each document, enabling the reranker to significantly reduce the HD proportion. Experiments and analysis across multiple models and datasets, including Wikipedia, web news, and research papers, show the effectiveness of our method. Our code is available at https://github.com/lzz335/hidden_risk_of_reranking.
Recent studies show that claims incorporating both text and images spread more effectively than those with text alone, presenting significant challenges for multimodal fact-checking. The rapid development of Multi-modal Large Language Models (MLLMs) has greatly advanced research in this field, enabling stronger performance. However, existing MLLM-based fact-checking methods fail to fully exploit visual evidence, and their reliance on rigid fine-tuning templates limits context-aware explanations and leads to weak deep reasoning. To address these limitations, we propose FACTCOMPASS, a novel framework that combines reasoning-aware fine-tuning with large-scale rule-based reinforcement learning and incorporates a semantic- and knowledge-enhanced retrieval module to strengthen deep reasoning and improve evidence utilization. This framework enhances evidence retrieval by obtaining semantically relevant evidence images, enriching the contextual understanding of claim-related images, and refining textual evidence at the knowledge level. To further enhance reasoning, we introduce a self-refining reinforcement fine-tuning strategy: (1) distilling GPT-4o's reasoning from partially fact-checking data for cold-start Chain-of-Thought learning; (2) activating reasoning across broader datasets using prior knowledge and rejection sampling; (3) applying Group Relative Policy Optimization to explore diverse reasoning paths and optimize factual consistency. Extensive experiments have demonstrated the effectiveness of the proposed framework.
Retrieval-Augmented Generation (RAG) systems are widely adopted in question answering, yet they often fail to satisfy complex multi-constraint queries, leading to constraint violations, factual inconsistencies, or hallucinations. We present Structure-Driven RAG System for Multi-Constraint Queries(MC-RAG), a structure-driven RAG system that reformulates retrieval as a subgraph matching problem over a knowledge graph. By integrating semantic and structural embeddings with path-level indexing, MC-RAG performs interpretable, structure-aware, and constraint-consistent retrieval and generation. During the demonstration, participants can input medical or encyclopedic multi-constraint queries, visualize how the system parses constraints, performs structural matching, and generates answers, thereby experiencing an end-to-end, interactive, and explainable RAG pipeline. A demo video is available at https://youtu.be/J8kahzmAnu0.
Large Language Models (LLMs) excel in natural language processing (NLP) tasks. However, they suffer from inherent limitations due to their sequence-based nature, such as structural information loss and factual unreliability. Graphs, with the ability to explicitly model entities and relations, offer an effective way to address these shortcomings. To systematically synthesize the emerging research on graph-enhanced LLMs, this survey, Graph4LLM, examines how these methods integrate graphs into various stages of the LLM pipeline, including the input, model, and output phases. For each phase, we provide a detailed review of the key methods and techniques. We also introduce a wide range of application scenarios where Graph4LLM methods demonstrate significant potential. Finally, we outline the challenges and future research directions for developing more efficient and interpretable solutions.
Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings where factual errors and ideological distortions are high-stakes. We present a reproducible measurement framework that treats hallucinations, unsupported statements in document-grounded QA, as diagnostic signals of ideological drift. Using 21,727 expert-labeled U.S. political news articles from QBias spanning left, center, and right sources, we (i) generate an article-specific question, (ii) elicit document-grounded answers from three open-weight LLMs and one proprietary model, (iii) detect sentence-level hallucinations via reference-based comparison, (iv) classify the ideological valence of hallucinated sentences with a fine-tuned stance classifier, and (v) probe output logits to relate token-level uncertainty to hallucination and drift. Hallucination rates vary substantially across models and concentrate in contentious topics, while source-ideology differences in hallucination frequency are modest. In contrast, hallucination content exhibits robust leftward drift: a majority of hallucinated sentences are classified as left-leaning, including among hallucinations generated from right-leaning sources. Logit-level analysis shows hallucinations arise in high-entropy generation contexts, and in some models uncertainty also predicts leftward drift, consistent with an "uncertainty → guessing" mechanism. We discuss implications for auditing AI-mediated political information and for designing safeguards in election-relevant deployments.
In multi-turn interactions, large language models (LLMs) often exhibit a persistent influence from prior turns, even after an explicit topic switch. This behavior, which we term semantic inertia, can cause responses to deviate from the expected output distribution for an independent task, undermining task isolation and reliability. This paper introduces a rigorous experimental framework to systematically characterize the nature, form, and dynamics of semantic inertia. We propose an operational definition and a causal-contrastive method that isolates semantic carryover from confounding factors like context length. Through a series of experiments on five leading LLMs, we (i) confirm the existence of semantic inertia and identify its boundary conditions; (ii) model its decay over the course of generation, revealing a characteristic timescale and a heavy-tailed distribution; (iii) decompose its effects on three distinct channels—factual accuracy, structural integrity, and stylistic expression; and (iv) probe its controllability using prompt-based interventions. Our key findings show that inertia is not a simple length effect but an intrinsic dynamic, strongest in the initial part of a generation and decaying over a timescale of approximately 100-200 tokens. Its impact is most pronounced as a stylistic residue, while its effect on factual correctness is weaker and highly dependent on the task and domain switch. Crucially, we find that prompt-level ``reset'' instructions are unreliable and often counter-productive, while conflicting constraints consistently amplify, rather than resolve, output deviation. These results suggest that governing semantic inertia requires system-level state management mechanisms rather than relying on prompt engineering alone.