{"list":"other","total":60,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"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":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"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":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2310.05189","title":"Factuality Challenges in the Era of Large Language Models","created":"2023-10-08","cited_by_count":126},{"id":"2406.19276","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","created":"2024-06-27","cited_by_count":117},{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113},{"id":"2210.13777","title":"SciFact-Open: Towards open-domain scientific claim verification","created":"2022-10-25","cited_by_count":94},{"id":"2401.03205","title":"The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models","created":"2024-01-06","cited_by_count":88},{"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},{"id":"2010.05873","title":"Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data","created":"2020-10-12","cited_by_count":84},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66},{"id":"2305.13712","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","created":"2023-05-23","cited_by_count":61},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54},{"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":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50},{"id":"2312.05200","title":"DelucionQA: Detecting Hallucinations in Domain-specific Question Answering","created":"2023-12-08","cited_by_count":43},{"id":"2403.03558","title":"Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem","created":"2024-03-06","cited_by_count":43},{"id":"2310.06498","title":"A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection","created":"2023-10-10","cited_by_count":42},{"id":"2310.03368","title":"Evaluating Hallucinations in Chinese Large Language Models","created":"2023-10-05","cited_by_count":33},{"id":"1805.04843","title":"Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders","created":"2018-05-13","cited_by_count":26},{"id":"2405.14486","title":"RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models","created":"2024-05-23","cited_by_count":25},{"id":"2407.04693","title":"ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models","created":"2024-07-05","cited_by_count":14},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9},{"id":"2405.20315","title":"ANAH: Analytical Annotation of Hallucinations in Large Language Models","created":"2024-05-30","cited_by_count":7}],"next_cursor":null}