{"total":37,"rows":[{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"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":"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":"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":"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":"2508.05201","title":"FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance","created":"2025-08-07","cited_by_count":8,"area":null},{"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":"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":"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":"2506.06539","title":"Beyond Facts: Evaluating Intent Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"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":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2509.22582","title":"Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs","created":"2025-09-26","cited_by_count":1,"area":null},{"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":"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":"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":"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":"2608.20204","title":"ContractScrub: A benchmark for final review of legal contracts","created":"2026-08-20","cited_by_count":1,"area":null},{"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":"2511.03900","title":"GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation","created":"2025-11-05","cited_by_count":0,"area":null},{"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":"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":"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":"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":"2609.38851","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}