{"total":73,"rows":[{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2505.08617","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","created":"2025-05-13","cited_by_count":163,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2501.03124","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","created":"2025-01-06","cited_by_count":99,"area":"lr"},{"id":"2506.01062","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","created":"2025-06-01","cited_by_count":75,"area":"lr"},{"id":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53,"area":"lr"},{"id":"2410.08145","title":"Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs","created":"2024-10-10","cited_by_count":38,"area":"mllm"},{"id":"2408.17150","title":"Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning","created":"2024-08-30","cited_by_count":23,"area":"lr"},{"id":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2505.19509","title":"Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models","created":"2025-05-26","cited_by_count":19,"area":"mllm"},{"id":"2410.16090","title":"Analysing the Residual Stream of Language Models Under Knowledge Conflicts","created":"2024-10-21","cited_by_count":17,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2412.14368","title":"Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs","created":"2024-12-18","cited_by_count":12,"area":"lr"},{"id":"2601.03746","title":"Whose Facts Win? LLM Source Preferences under Knowledge Conflicts","created":"2026-01-07","cited_by_count":12,"area":"rag"},{"id":"2409.14083","title":"SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information","created":"2024-09-21","cited_by_count":11,"area":"mllm"},{"id":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2506.05154","title":"Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement","created":"2025-06-05","cited_by_count":11,"area":"rag"},{"id":"2503.12821","title":"From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration","created":"2025-03-17","cited_by_count":8,"area":"mllm"},{"id":"2505.09787","title":"A Multimodal Multi-Agent Framework for Radiology Report Generation","created":"2025-05-14","cited_by_count":8,"area":"agents"},{"id":"2505.22787","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2510.02608","title":"Mitigating Modal Imbalance in Multimodal Reasoning","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2503.23361","title":"Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base","created":"2025-03-30","cited_by_count":6,"area":null},{"id":"2508.11957","title":"A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond","created":"2025-08-16","cited_by_count":6,"area":"agents"},{"id":"2601.06842","title":"Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation","created":"2026-01-11","cited_by_count":6,"area":"rag"},{"id":"2411.06438","title":"Conditional [MASK] Discrete Diffusion Language Model","created":"2024-11-10","cited_by_count":5,"area":"diffusion"},{"id":"2505.21608","title":"How does Misinformation Affect Large Language Model Behaviors and Preferences?","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2508.12355","title":"Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-Answering","created":"2025-08-17","cited_by_count":5,"area":null},{"id":"2505.17118","title":"After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in Retrieval-Augmented Generation","created":"2025-05-21","cited_by_count":4,"area":"rag"},{"id":"2508.15793","title":"Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2505.22318","title":"Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2601.11886","title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence","created":"2026-01-17","cited_by_count":3,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2502.18573","title":"FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models","created":"2025-02-25","cited_by_count":2,"area":"lr"},{"id":"2506.05278","title":"Micro-Act: Mitigating Knowledge Conflict in LLM-based RAG via Actionable Self-Reasoning","created":"2025-06-05","cited_by_count":2,"area":"lr"},{"id":"2510.07926","title":"Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.19172","title":"When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2603.15892","title":"Temporal Fact Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.23750","title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","created":"2026-04-26","cited_by_count":2,"area":null},{"id":"2605.05632","title":"Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning","created":"2026-05-07","cited_by_count":2,"area":"rag"},{"id":"2605.12185","title":"Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.19341","title":"HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models","created":"2026-05-19","cited_by_count":2,"area":"wm"},{"id":"2505.21958","title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.02841","title":"A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering","created":"2025-08-04","cited_by_count":1,"area":"lr"},{"id":"2509.11967","title":"MillStone: How Open-Minded Are LLMs?","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2511.10881","title":"A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2602.14065","title":"REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment","created":"2026-02-15","cited_by_count":1,"area":null},{"id":"2602.14518","title":"Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2606.01120","title":"Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.20245","title":"Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2607.16019","title":"Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.06938","title":"Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2608.13921","title":"When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict","created":"2026-08-14","cited_by_count":1,"area":"agents"},{"id":"2609.01852","title":"The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.03588","title":"KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.30813","title":"A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2501.01332","title":"Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2508.20867","title":"MSRS: Evaluating Multi-Source Retrieval-Augmented Generation","created":"2025-08-28","cited_by_count":0,"area":"rag"},{"id":"2510.17890","title":"MIN-Merging: Merge the Important Neurons for Model Merging","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2512.16795","title":"From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs","created":"2025-12-18","cited_by_count":0,"area":"lr"},{"id":"2601.11232","title":"FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2607.22625","title":"TokenMem: Faithful Knowledge Injection for Frozen LLMs","created":"2026-06-17","cited_by_count":0,"area":"rag"},{"id":"2607.24117","title":"Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.08236","title":"LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2608.16515","title":"When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2608.25894","title":"From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28478","title":"Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.22043","title":"An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.36748","title":"Generalizable Lifelong Model Editing via Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.39473","title":"Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00568","title":"Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.12360","title":"Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}