{"list":"other","total":57,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"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":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"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":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"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":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"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":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2306.16092","title":"Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture","created":"2023-06-28","cited_by_count":122},{"id":"2402.03578","title":"LLM Multi-Agent Systems: Challenges and Open Problems","created":"2024-02-05","cited_by_count":120},{"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":"2310.00305","title":"Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method","created":"2023-09-30","cited_by_count":97},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"2310.00741","title":"FELM: Benchmarking Factuality Evaluation of Large Language Models","created":"2023-10-01","cited_by_count":66},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50},{"id":"2404.07221","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","created":"2024-03-23","cited_by_count":49},{"id":"2411.07140","title":"Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models","created":"2024-11-11","cited_by_count":43},{"id":"2411.00784","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","created":"2024-10-17","cited_by_count":39},{"id":"2407.21065","title":"LawLLM: Law Large Language Model for the US Legal System","created":"2024-07-27","cited_by_count":37},{"id":"2310.03368","title":"Evaluating Hallucinations in Chinese Large Language Models","created":"2023-10-05","cited_by_count":33},{"id":"2402.10986","title":"FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models","created":"2024-02-16","cited_by_count":32},{"id":"2305.14623","title":"Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models","created":"2023-05-24","cited_by_count":31},{"id":"2310.13549","title":"The Perils & Promises of Fact-checking with Large Language Models","created":"2023-10-20","cited_by_count":31},{"id":"2410.12971","title":"Self-Pluralising Culture Alignment for Large Language Models","created":"2024-10-16","cited_by_count":31},{"id":"2404.12065","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","created":"2024-04-18","cited_by_count":27},{"id":"2410.22257","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","created":"2024-10-29","cited_by_count":25},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19},{"id":"2407.03453","title":"On Large Language Models in National Security Applications","created":"2024-07-03","cited_by_count":19},{"id":"2412.20127","title":"M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation","created":"2024-12-28","cited_by_count":13},{"id":"2310.10429","title":"Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting","created":"2023-10-16","cited_by_count":11},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8},{"id":"2412.13268","title":"JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment","created":"2024-12-17","cited_by_count":6},{"id":"2407.20588","title":"Enhancing Agricultural Machinery Management through Advanced LLM Integration","created":"2024-07-30","cited_by_count":1}],"next_cursor":null}