{"total":86,"rows":[{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"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":"2504.13079","title":"Retrieval-Augmented Generation with Conflicting Evidence","created":"2025-04-17","cited_by_count":63,"area":"rag"},{"id":"2412.15280","title":"Context-DPO: Aligning Language Models for Context-Faithfulness","created":"2024-12-18","cited_by_count":50,"area":"alignment"},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2502.14302","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","created":"2025-02-20","cited_by_count":34,"area":null},{"id":"2506.08938","title":"FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation","created":"2025-06-10","cited_by_count":28,"area":"rag"},{"id":"2509.09660","title":"Steering MoE LLMs via Expert (De)Activation","created":"2025-09-11","cited_by_count":26,"area":"moe"},{"id":"2410.14675","title":"To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts","created":"2024-10-18","cited_by_count":25,"area":"rag"},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25,"area":"rag"},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20,"area":"rag"},{"id":"2503.14603","title":"Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11,"area":"rag"},{"id":"2505.16483","title":"Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning","created":"2025-05-22","cited_by_count":11,"area":null},{"id":"2506.11930","title":"Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2605.19196","title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","created":"2026-05-18","cited_by_count":10,"area":"agents"},{"id":"2510.10390","title":"RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models","created":"2025-10-12","cited_by_count":9,"area":"rag"},{"id":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2504.20119","title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","created":"2025-04-28","cited_by_count":7,"area":"rag"},{"id":"2511.08409","title":"Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs","created":"2025-11-11","cited_by_count":7,"area":"lr"},{"id":"2507.18043","title":"GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs","created":"2025-07-24","cited_by_count":6,"area":"mllm"},{"id":"2510.01782","title":"Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"id":"2410.16672","title":"The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models","created":"2024-10-22","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":"2412.12300","title":"Unanswerability Evaluation for Retrieval Augmented Generation","created":"2024-12-16","cited_by_count":4,"area":"rag"},{"id":"2504.14856","title":"Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation","created":"2025-04-21","cited_by_count":4,"area":"rag"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2512.06476","title":"Knowing What's Missing: Assessing Information Sufficiency in Question Answering","created":"2025-12-06","cited_by_count":3,"area":null},{"id":"2606.07874","title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2608.06377","title":"Learning When to Trust via Selective Context Preference Optimization","created":"2026-08-06","cited_by_count":3,"area":"alignment"},{"id":"2502.19779","title":"Do Retrieval-Augmented Language Models Adapt to Varying User Needs?","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2506.06539","title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2510.00508","title":"Copy-Paste to Mitigate Large Language Model Hallucinations","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2510.12460","title":"Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation","created":"2025-10-14","cited_by_count":2,"area":"rag"},{"id":"2602.23952","title":"CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2607.12650","title":"Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2502.12502","title":"Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2509.22582","title":"Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2601.08676","title":"Advancing ESG Intelligence: An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance","created":"2026-01-13","cited_by_count":1,"area":"agents"},{"id":"2602.22584","title":"Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.04406","title":"CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.17943","title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.22335","title":"Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding","created":"2026-04-24","cited_by_count":1,"area":"safety"},{"id":"2604.25313","title":"Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models","created":"2026-04-28","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2605.17356","title":"UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings","created":"2026-05-17","cited_by_count":1,"area":null},{"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":"2606.04109","title":"Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09005","title":"Document-Authored Control-Signal Impersonation: A Low-Cost Indirect Prompt Attack on RAG Safety Boundaries","created":"2026-06-08","cited_by_count":1,"area":"rag"},{"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":"2607.19355","title":"Information Discernment in Large Language Models","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2608.07933","title":"EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation","created":"2026-08-08","cited_by_count":1,"area":"rag"},{"id":"2608.20204","title":"ContractScrub: A benchmark for final review of legal contracts","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.26295","title":"MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2608.28018","title":"Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2503.07144","title":"MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2503.07587","title":"Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru","created":"2025-03-10","cited_by_count":0,"area":"driving"},{"id":"2511.03900","title":"GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.02023","title":"Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs","created":"2026-01-05","cited_by_count":0,"area":"lr"},{"id":"2602.08149","title":"DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2605.07186","title":"The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.26362","title":"Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.00683","title":"OCC-RAG: Optimal Cognitive Core for Faithful Question Answering","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.12903","title":"X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation","created":"2026-06-11","cited_by_count":0,"area":"rag"},{"id":"2606.13316","title":"ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.00661","title":"Faithful by Definition: Emotion Analysis via Natural Semantic Metalanguage Explications","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.15957","title":"From Plausible to Actionable: A Position on LLM Self-Explanations","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.21961","title":"On Improving Faithfulness of Podcasts from Documents","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.25953","title":"Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27637","title":"MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.04286","title":"Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"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":"2608.20554","title":"aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.29798","title":"R$^2$A: Learning Persona Policies Through Persona Representation Learning and Runtime Alignment","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.00508","title":"CoVer: Conflict-Aware Claim Verification","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01687","title":"Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04647","title":"CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"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":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.25602","title":"Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs","created":"2026-09-22","cited_by_count":0,"area":"mechinterp"},{"id":"2609.38851","title":"Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}