{"list":"other","total":109,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"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":"1604.04173","title":"Distribution-Free Predictive Inference For Regression","created":"2016-04-14","cited_by_count":668},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"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":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"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":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"1609.00451","title":"Least Ambiguous Set-Valued Classifiers with Bounded Error Levels","created":"2016-09-02","cited_by_count":272},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2202.07282","title":"Adaptive Conformal Predictions for Time Series","created":"2022-02-15","cited_by_count":161},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"1901.08079","title":"A Question-Entailment Approach to Question Answering","created":"2019-01-23","cited_by_count":134},{"id":"2104.08279","title":"Testing for Outliers with Conformal p-values","created":"2021-04-16","cited_by_count":134},{"id":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2208.08401","title":"Conformal Inference for Online Prediction with Arbitrary Distribution Shifts","created":"2022-08-17","cited_by_count":128},{"id":"2401.12794","title":"Benchmarking LLMs via Uncertainty Quantification","created":"2024-01-23","cited_by_count":126},{"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":"2106.08460","title":"Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction","created":"2021-06-15","cited_by_count":114},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"2308.13259","title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","created":"2023-08-25","cited_by_count":97},{"id":"2305.13160","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","created":"2023-05-22","cited_by_count":94},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"1302.6452","title":"A Conformal Prediction Approach to Explore Functional Data","created":"2013-02-26","cited_by_count":86},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"2402.13904","title":"Calibrating Large Language Models with Sample Consistency","created":"2024-02-21","cited_by_count":73},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69},{"id":"1802.06300","title":"Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Data","created":"2018-02-17","cited_by_count":66},{"id":"2305.11473","title":"Graphologue: Exploring Large Language Model Responses with Interactive Diagrams","created":"2023-05-19","cited_by_count":66},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65},{"id":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64},{"id":"2504.04717","title":"Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models","created":"2025-04-07","cited_by_count":62},{"id":"2001.00106","title":"PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction","created":"2019-12-31","cited_by_count":60},{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49},{"id":"2404.02655","title":"Calibrating the Confidence of Large Language Models by Eliciting Fidelity","created":"2024-04-03","cited_by_count":47},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46},{"id":"2106.09848","title":"PAC Prediction Sets Under Covariate Shift","created":"2021-06-17","cited_by_count":45},{"id":"2402.10189","title":"Uncertainty Quantification for In-Context Learning of Large Language Models","created":"2024-02-15","cited_by_count":45},{"id":"1905.04396","title":"Prediction and outlier detection in classification problems","created":"2019-05-10","cited_by_count":44},{"id":"2305.14323","title":"ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models","created":"2023-05-23","cited_by_count":43},{"id":"2205.09095","title":"Achieving Risk Control in Online Learning Settings","created":"2022-05-18","cited_by_count":39},{"id":"2402.03271","title":"Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models","created":"2024-02-05","cited_by_count":39},{"id":"2406.18814","title":"Length Optimization in Conformal Prediction","created":"2024-06-27","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":"1809.07441","title":"Distribution-Free Prediction Sets for Two-Layer Hierarchical Models","created":"2018-09-20","cited_by_count":35},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28},{"id":"2201.02331","title":"iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection","created":"2022-01-07","cited_by_count":27},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25},{"id":"2402.15131","title":"Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models","created":"2024-02-23","cited_by_count":25},{"id":"2310.01468","title":"Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games","created":"2023-10-02","cited_by_count":24},{"id":"2407.07140","title":"Cardinality-Aware Set Prediction and Top-$k$ Classification","created":"2024-07-09","cited_by_count":23},{"id":"2504.14154","title":"SConU: Selective Conformal Uncertainty in Large Language Models","created":"2025-04-19","cited_by_count":23},{"id":"2203.06126","title":"Prediction Sets Adaptive to Unknown Covariate Shift","created":"2022-03-11","cited_by_count":22},{"id":"2310.12964","title":"PAC Prediction Sets Under Label Shift","created":"2023-10-19","cited_by_count":21},{"id":"2402.02392","title":"DeLLMa: Decision Making Under Uncertainty with Large Language Models","created":"2024-02-04","cited_by_count":21},{"id":"2405.02140","title":"An Information Theoretic Perspective on Conformal Prediction","created":"2024-05-03","cited_by_count":21},{"id":"2502.06884","title":"Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models","created":"2025-02-08","cited_by_count":21},{"id":"2410.08174","title":"Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models","created":"2024-10-10","cited_by_count":19},{"id":"2207.02440","title":"PAC Prediction Sets for Meta-Learning","created":"2022-07-06","cited_by_count":16},{"id":"2411.02381","title":"Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI","created":"2024-11-04","cited_by_count":15},{"id":"2301.11556","title":"Conformal inference is (almost) free for neural networks trained with early stopping","created":"2023-01-27","cited_by_count":14},{"id":"2306.07254","title":"On the Expected Size of Conformal Prediction Sets","created":"2023-06-12","cited_by_count":13},{"id":"2503.08308","title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","created":"2025-03-11","cited_by_count":12},{"id":"2402.03719","title":"Empowering Language Models with Active Inquiry for Deeper Understanding","created":"2024-02-06","cited_by_count":11},{"id":"2205.10798","title":"PAC-Wrap: Semi-Supervised PAC Anomaly Detection","created":"2022-05-22","cited_by_count":10},{"id":"2211.04612","title":"Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries","created":"2022-11-09","cited_by_count":10},{"id":"2503.10512","title":"Conformal Prediction Sets for Deep Generative Models via Reduction to Conformal Regression","created":"2025-03-13","cited_by_count":10},{"id":"2108.08074","title":"MeDiaQA: A Question Answering Dataset on Medical Dialogues","created":"2021-08-18","cited_by_count":9},{"id":"2410.10864","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","created":"2024-10-07","cited_by_count":8},{"id":"2410.13115","title":"Online conformal inference for multi-step time series forecasting","created":"2024-10-17","cited_by_count":8},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7},{"id":"2504.18919","title":"Clinical knowledge in LLMs does not translate to human interactions","created":"2025-04-26","cited_by_count":7},{"id":"2309.08922","title":"Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models","created":"2023-09-16","cited_by_count":6},{"id":"2310.03293","title":"A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions","created":"2023-10-05","cited_by_count":6}],"next_cursor":"100"}