{"total":66,"rows":[{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2502.01236","title":"Eliciting Language Model Behaviors with Investigator Agents","created":"2025-02-03","cited_by_count":23,"area":"agents"},{"id":"2407.02351","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","created":"2024-07-02","cited_by_count":19,"area":null},{"id":"2410.01794","title":"Loki: An Open-Source Tool for Fact Verification","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2508.03860","title":"Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models","created":"2025-08-05","cited_by_count":13,"area":"rag"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2407.13578","title":"How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency","created":"2024-07-18","cited_by_count":10,"area":"lr"},{"id":"2506.06877","title":"Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning","created":"2025-06-07","cited_by_count":10,"area":"lr"},{"id":"2507.19364","title":"From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation","created":"2025-07-25","cited_by_count":10,"area":null},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2412.15265","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2503.12908","title":"HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2508.18880","title":"Challenges for Generative AI in Legal Reasoning","created":"2025-08-26","cited_by_count":7,"area":"lr"},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2508.00719","title":"DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2510.22581","title":"Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems","created":"2025-10-26","cited_by_count":5,"area":null},{"id":"2505.13761","title":"Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making","created":"2025-05-19","cited_by_count":4,"area":"agents"},{"id":"2506.06800","title":"On the Adaptive Psychological Persuasion of Large Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2507.08371","title":"The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality","created":"2025-07-11","cited_by_count":4,"area":"synth"},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2607.01243","title":"STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2506.13171","title":"Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches","created":"2025-06-16","cited_by_count":3,"area":"agents"},{"id":"2512.23547","title":"Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2403.18976","title":"\"Sorry, Come Again?\" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2504.02865","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2505.17125","title":"NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.09360","title":"MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems","created":"2025-09-11","cited_by_count":2,"area":"rag"},{"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":"2510.10890","title":"LLM$\\times$MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2602.11166","title":"Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2502.12821","title":"Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2505.23291","title":"ScEdit: Script-based Assessment of Knowledge Editing","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.09886","title":"Probabilistic distances-based hallucination detection in LLMs with RAG","created":"2025-06-11","cited_by_count":1,"area":"rag"},{"id":"2508.20417","title":"KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval","created":"2025-08-28","cited_by_count":1,"area":"rag"},{"id":"2601.06519","title":"MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation","created":"2026-01-10","cited_by_count":1,"area":"rag"},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.19843","title":"Overreliance on AI in Information-seeking from Video Content","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.09497","title":"Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces","created":"2026-05-10","cited_by_count":1,"area":"agents"},{"id":"2605.20005","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.28187","title":"Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2506.11110","title":"AssertBench: A Benchmark for Evaluating Self-Assertion in Large Language Models","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2509.00325","title":"GIER: Gap-Driven Self-Refinement for Large Language Models","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2509.03962","title":"Exploring NLP Benchmarks in an Extremely Low-Resource Setting","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.24212","title":"ScenarioBench: Trace-Grounded Compliance Evaluation for Text-to-SQL and RAG","created":"2025-09-29","cited_by_count":0,"area":"rag"},{"id":"2509.26406","title":"An Annotation Scheme for Factuality and its Application to Parliamentary Proceedings","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.02001","title":"Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2512.14887","title":"Integrating Large Language Models and Knowledge Graphs to Capture Political Viewpoints in News Media","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.00848","title":"Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.03417","title":"FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.11939","title":"Do Large Language Models Adapt to Language Variation across Socioeconomic Status?","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.11689","title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.24076","title":"An Information-Geometric Framework for Stability Analysis of Large Language Models under Entropic Stress","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.14449","title":"When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.18163","title":"TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.16868","title":"Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.20794","title":"Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00492","title":"The Privacy-Hallucination Tradeoff in Differentially Private Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.12884","title":"MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15561","title":"Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.31422","title":"Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.07787","title":"OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}