{"total":43,"rows":[{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"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":"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":"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":"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":"2506.06800","title":"On the Adaptive Psychological Persuasion of Large Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"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":"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":"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":"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":"2505.23291","title":"ScEdit: Script-based Assessment of Knowledge Editing","created":"2025-05-29","cited_by_count":1,"area":null},{"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":"2605.20005","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":"2509.26406","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":"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}],"next_cursor":null}