{"list":"other","total":62,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"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":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"2311.07397","title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation","created":"2023-11-13","cited_by_count":300},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88},{"id":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86},{"id":"2408.12076","title":"ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM","created":"2024-08-22","cited_by_count":73},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52},{"id":"1612.03969","title":"Tracking the World State with Recurrent Entity Networks","created":"2016-12-12","cited_by_count":51},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48},{"id":"2306.07934","title":"BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information","created":"2023-06-13","cited_by_count":44},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39},{"id":"2501.08292","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","created":"2025-01-14","cited_by_count":34},{"id":"2407.15680","title":"HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning","created":"2024-07-22","cited_by_count":32},{"id":"2408.03617","title":"Is Child-Directed Speech Effective Training Data for Language Models?","created":"2024-08-07","cited_by_count":24},{"id":"2410.13210","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","created":"2024-10-17","cited_by_count":24},{"id":"2404.07461","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","created":"2024-04-11","cited_by_count":17},{"id":"2406.10447","title":"The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences","created":"2024-06-14","cited_by_count":17},{"id":"2507.21017","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them","created":"2025-07-28","cited_by_count":16},{"id":"2601.06818","title":"AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents","created":"2026-01-11","cited_by_count":16},{"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":"2108.06643","title":"SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation","created":"2021-08-15","cited_by_count":8},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7},{"id":"2210.04191","title":"CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models","created":"2022-10-09","cited_by_count":7},{"id":"2404.01588","title":"Hallucination Diversity-Aware Active Learning for Text Summarization","created":"2024-04-02","cited_by_count":5},{"id":"2603.29552","title":"Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models","created":"2026-03-31","cited_by_count":5},{"id":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2},{"id":"2603.29522","title":"Baby Scale: Investigating Models Trained on Individual Children's Language Input","created":"2026-03-31","cited_by_count":2}],"next_cursor":null}