{"list":"other","total":56,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"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":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"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":"2107.07511","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","created":"2021-07-15","cited_by_count":792},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"1604.04173","title":"Distribution-Free Predictive Inference For Regression","created":"2016-04-14","cited_by_count":668},{"id":"1905.03222","title":"Conformalized Quantile Regression","created":"2019-05-08","cited_by_count":629},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2006.02544","title":"Classification with Valid and Adaptive Coverage","created":"2020-06-03","cited_by_count":396},{"id":"2106.00170","title":"Adaptive Conformal Inference Under Distribution Shift","created":"2021-06-01","cited_by_count":375},{"id":"2009.14193","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","created":"2020-09-29","cited_by_count":366},{"id":"2202.13415","title":"Conformal prediction beyond exchangeability","created":"2022-02-27","cited_by_count":355},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2208.02814","title":"Conformal Risk Control","created":"2022-08-04","cited_by_count":299},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271},{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"1810.08240","title":"Time-uniform, nonparametric, nonasymptotic confidence sequences","created":"2018-10-18","cited_by_count":229},{"id":"2310.02124","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","created":"2023-10-03","cited_by_count":222},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"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":"2402.05120","title":"More Agents Is All You Need","created":"2024-02-03","cited_by_count":180},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2010.09686","title":"Estimating means of bounded random variables by betting","created":"2020-10-19","cited_by_count":169},{"id":"1902.06977","title":"Evaluating model calibration in classification","created":"2019-02-19","cited_by_count":168},{"id":"2210.01948","title":"Game-theoretic statistics and safe anytime-valid inference","created":"2022-10-04","cited_by_count":155},{"id":"2305.12616","title":"Conformal Prediction With Conditional Guarantees","created":"2023-05-22","cited_by_count":152},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2106.08460","title":"Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction","created":"2021-06-15","cited_by_count":114},{"id":"1906.07801","title":"Safe Testing","created":"2019-06-18","cited_by_count":101},{"id":"2006.10564","title":"Distribution-free binary classification: prediction sets, confidence intervals and calibration","created":"2020-06-18","cited_by_count":79},{"id":"2107.05719","title":"Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration","created":"2021-07-12","cited_by_count":79},{"id":"2211.16886","title":"A Unifying Theory of Distance from Calibration","created":"2022-11-30","cited_by_count":53},{"id":"2009.03167","title":"Admissible anytime-valid sequential inference must rely on nonnegative martingales","created":"2020-09-07","cited_by_count":48},{"id":"2310.07850","title":"Conformal prediction with local weights: randomization enables local guarantees","created":"2023-10-11","cited_by_count":48},{"id":"2402.01766","title":"LLM Voting: Human Choices and AI Collective Decision Making","created":"2024-01-31","cited_by_count":48},{"id":"2202.07650","title":"Conformal Prediction Sets with Limited False Positives","created":"2022-02-15","cited_by_count":28},{"id":"2406.12197","title":"Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction","created":"2024-06-18","cited_by_count":10}],"next_cursor":null}