{"total":88,"rows":[{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2403.11116","title":"PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset","created":"2024-03-17","cited_by_count":45,"area":"mllm"},{"id":"2405.19648","title":"Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach","created":"2024-05-30","cited_by_count":42,"area":null},{"id":"2405.13873","title":"FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering","created":"2024-05-22","cited_by_count":39,"area":"lr"},{"id":"2502.02871","title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","created":"2025-02-05","cited_by_count":33,"area":"lr"},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2406.07070","title":"HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation","created":"2024-06-11","cited_by_count":27,"area":null},{"id":"2410.18860","title":"DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations","created":"2024-10-24","cited_by_count":25,"area":null},{"id":"2410.14479","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","created":"2024-10-18","cited_by_count":22,"area":"rag"},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2404.00216","title":"Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness","created":"2024-03-30","cited_by_count":17,"area":null},{"id":"2505.24478","title":"Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning","created":"2025-05-30","cited_by_count":17,"area":"lr"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16,"area":"agents"},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2403.14401","title":"Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination","created":"2024-03-21","cited_by_count":14,"area":"mllm"},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2404.10513","title":"CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity","created":"2024-04-16","cited_by_count":12,"area":"lr"},{"id":"2410.02899","title":"FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs","created":"2024-10-03","cited_by_count":11,"area":null},{"id":"2503.05318","title":"Uncertainty-Aware Decoding with Minimum Bayes Risk","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2601.09028","title":"OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG","created":"2026-01-13","cited_by_count":11,"area":"rag"},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2504.09482","title":"HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs","created":"2025-04-13","cited_by_count":8,"area":null},{"id":"2505.00019","title":"An Empirical Study on Prompt Compression for Large Language Models","created":"2025-04-24","cited_by_count":8,"area":"inference"},{"id":"2406.09155","title":"DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2412.17534","title":"CiteBART: Learning to Generate Citations for Local Citation Recommendation","created":"2024-12-23","cited_by_count":6,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.05497","title":"Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2506.11124","title":"Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Prompting","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2605.15208","title":"Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels","created":"2026-05-02","cited_by_count":6,"area":null},{"id":"2506.13130","title":"ZINA: Multimodal Fine-grained Hallucination Detection and Editing","created":"2025-06-16","cited_by_count":5,"area":"mllm"},{"id":"2510.17733","title":"Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations","created":"2025-10-20","cited_by_count":5,"area":"rag"},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2411.09255","title":"DAHL: Domain-specific Automated Hallucination Evaluation of Long-Form Text through a Benchmark Dataset in Biomedicine","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2507.20836","title":"First Hallucination Tokens Are Different from Conditional Ones","created":"2025-07-28","cited_by_count":4,"area":null},{"id":"2509.13154","title":"LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2606.31134","title":"Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics","created":"2026-06-30","cited_by_count":4,"area":"lr"},{"id":"2512.02299","title":"HealthContradict: Evaluating Biomedical Knowledge Conflicts in Language Models","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.04742","title":"Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval","created":"2026-01-08","cited_by_count":3,"area":"agents"},{"id":"2602.06920","title":"Halluverse-M^3: A multitask multilingual benchmark for hallucination in LLMs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2603.00801","title":"The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2605.26366","title":"Automatic Layer Selection for Hallucination Detection","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2410.15460","title":"Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training","created":"2024-10-20","cited_by_count":2,"area":null},{"id":"2410.15966","title":"Self-Explained Keywords Empower Large Language Models for Code Generation","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2502.13490","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","created":"2025-02-19","cited_by_count":2,"area":"lr"},{"id":"2503.23415","title":"An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering","created":"2025-03-30","cited_by_count":2,"area":"agents"},{"id":"2505.00557","title":"Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2505.20336","title":"MOSLIM:Align with diverse preferences in prompts through reward classification","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2507.23356","title":"Quality Evaluation of COBOL to Java Code Transformation","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2512.03671","title":"Generative AI Practices, Literacy, and Divides: An Empirical Analysis in the Italian Context","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2512.06255","title":"Language-driven Fine-grained Retrieval","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","cited_by_count":2,"area":"synth"},{"id":"2503.21813","title":"OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2509.23580","title":"LLM Hallucination Detection: HSAD","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.23217","title":"Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2511.04502","title":"RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG","created":"2025-11-06","cited_by_count":1,"area":"rag"},{"id":"2603.20252","title":"FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.03205","title":"From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2410.18105","title":"Improving Embedding Accuracy for Document Retrieval Using Entity Relationship Maps and Model-Aware Contrastive Sampling","created":"2024-10-08","cited_by_count":0,"area":"rag"},{"id":"2412.02149","title":"Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2503.21544","title":"SWI: Speaking with Intent in Large Language Models","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.17345","title":"The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2509.05741","title":"Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification","created":"2025-09-06","cited_by_count":0,"area":"lr"},{"id":"2509.21473","title":"Are Hallucinations Bad Estimations?","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.21865","title":"Beyond RAG vs. Long-Context: Learning Distraction-Aware Retrieval for Efficient Knowledge Grounding","created":"2025-09-26","cited_by_count":0,"area":"rag"},{"id":"2510.02326","title":"Hallucination-Resistant, Domain-Specific Research Assistant with Self-Evaluation and Vector-Grounded Retrieval","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2511.03934","title":"PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2512.05700","title":"Faithfulness metric fusion: Improving the evaluation of LLM trustworthiness across domains","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.11110","title":"FIBER: A Multilingual Evaluation Resource for Factual Inference Bias","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.09486","title":"Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.12781","title":"The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Design","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.28828","title":"Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2606.08705","title":"Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.05477","title":"Decision Protocols in Multi-Agent Large Language Model Conversations","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2608.01322","title":"Can Language Models Identify Shadow Trading Targets? An NLP Evaluation of SEC Enforcement Theory","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.16353","title":"HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","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":"2609.32964","title":"The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining","created":"2026-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2609.35308","title":"Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}