{"list":"other","total":67,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2407.21771","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","created":"2024-07-31","cited_by_count":179},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65},{"id":"1808.09352","title":"Evaluating Theory of Mind in Question Answering","created":"2018-08-28","cited_by_count":64},{"id":"2208.05309","title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","created":"2022-08-10","cited_by_count":61},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39},{"id":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35},{"id":"2501.08292","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","created":"2025-01-14","cited_by_count":34},{"id":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29},{"id":"2506.08938","title":"FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation","created":"2025-06-10","cited_by_count":28},{"id":"2412.15285","title":"Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining","created":"2024-12-18","cited_by_count":26},{"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},{"id":"2506.08500","title":"DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs","created":"2025-06-10","cited_by_count":25},{"id":"2410.15737","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","created":"2024-10-21","cited_by_count":21},{"id":"2408.03297","title":"KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models","created":"2024-08-06","cited_by_count":20},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18},{"id":"2404.07461","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","created":"2024-04-11","cited_by_count":17},{"id":"2406.06326","title":"Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching","created":"2024-06-10","cited_by_count":17},{"id":"2508.19598","title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning","created":"2025-08-27","cited_by_count":17},{"id":"2503.05212","title":"Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning","created":"2025-03-07","cited_by_count":16},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16},{"id":"2311.08011","title":"Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models","created":"2023-11-14","cited_by_count":15},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15},{"id":"2412.13582","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","created":"2024-12-18","cited_by_count":13},{"id":"2404.06283","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","created":"2024-04-09","cited_by_count":12},{"id":"2502.00158","title":"Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating","created":"2025-01-31","cited_by_count":12},{"id":"2503.05703","title":"What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces","created":"2025-02-10","cited_by_count":12},{"id":"2305.19240","title":"NetHack is Hard to Hack","created":"2023-05-30","cited_by_count":11},{"id":"2506.05154","title":"Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement","created":"2025-06-05","cited_by_count":11},{"id":"2305.18582","title":"Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy","created":"2023-05-29","cited_by_count":10},{"id":"2506.04041","title":"LexTime: A Benchmark for Temporal Ordering of Legal Events","created":"2025-06-04","cited_by_count":10},{"id":"2109.03892","title":"Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models","created":"2021-09-08","cited_by_count":9},{"id":"2406.11830","title":"Language Modeling with Editable External Knowledge","created":"2024-06-17","cited_by_count":9},{"id":"2108.06643","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","created":"2021-08-15","cited_by_count":8},{"id":"2210.04191","title":"CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models","created":"2022-10-09","cited_by_count":7},{"id":"2506.15732","title":"Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning","created":"2025-06-15","cited_by_count":7},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","cited_by_count":3},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3},{"id":"2509.10708","title":"SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation","created":"2025-09-12","cited_by_count":2}],"next_cursor":null}