{"list":"other","total":64,"rows":[{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","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":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"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":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"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":"2001.02114","title":"Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making","created":"2020-01-07","cited_by_count":281},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"id":"2307.01379","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","created":"2023-07-03","cited_by_count":150},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111},{"id":"2401.13835","title":"What Large Language Models Know and What People Think They Know","created":"2024-01-24","cited_by_count":110},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106},{"id":"2302.13439","title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","created":"2023-02-26","cited_by_count":91},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62},{"id":"2404.00474","title":"Linguistic Calibration of Long-Form Generations","created":"2024-03-30","cited_by_count":60},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59},{"id":"2409.00097","title":"Large Language Models for Disease Diagnosis: A Scoping Review","created":"2024-08-27","cited_by_count":51},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48},{"id":"2512.15567","title":"Evaluating Large Language Models in Scientific Discovery","created":"2025-12-17","cited_by_count":42},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41},{"id":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32},{"id":"2410.22685","title":"Improving Uncertainty Quantification in Large Language Models via Semantic Embeddings","created":"2024-10-30","cited_by_count":30},{"id":"2406.03441","title":"Cycles of Thought: Measuring LLM Confidence through Stable Explanations","created":"2024-06-05","cited_by_count":29},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29},{"id":"2402.17124","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","created":"2024-02-27","cited_by_count":27},{"id":"2409.12180","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","created":"2024-09-18","cited_by_count":26},{"id":"2402.11406","title":"Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection","created":"2024-02-18","cited_by_count":25},{"id":"2504.14045","title":"Metacognition and Uncertainty Communication in Humans and Large Language Models","created":"2025-04-18","cited_by_count":23},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20},{"id":"2401.08694","title":"Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation","created":"2024-01-13","cited_by_count":19},{"id":"2203.17217","title":"On the probability-quality paradox in language generation","created":"2022-03-31","cited_by_count":16},{"id":"2505.24778","title":"Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?","created":"2025-05-30","cited_by_count":16},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15},{"id":"2411.02381","title":"Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI","created":"2024-11-04","cited_by_count":15},{"id":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13},{"id":"2410.04315","title":"Calibrating Expressions of Certainty","created":"2024-10-06","cited_by_count":7},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","cited_by_count":7},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","cited_by_count":7},{"id":"2510.12587","title":"Teaching Language Models to Faithfully Express their Uncertainty","created":"2025-10-14","cited_by_count":7},{"id":"2509.24202","title":"Can Large Language Models Express Uncertainty Like Human?","created":"2025-09-29","cited_by_count":5}],"next_cursor":null}