{"list":"other","total":66,"rows":[{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"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":"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":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"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":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"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":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"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":"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":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104},{"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":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67},{"id":"2503.00172","title":"A Survey of Uncertainty Estimation Methods on Large Language Models","created":"2025-02-28","cited_by_count":62},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61},{"id":"2404.00474","title":"Linguistic Calibration of Long-Form Generations","created":"2024-03-30","cited_by_count":60},{"id":"2308.05342","title":"Metacognitive Prompting Improves Understanding in Large Language Models","created":"2023-08-10","cited_by_count":58},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44},{"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":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39},{"id":"2405.16282","title":"Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models","created":"2024-05-25","cited_by_count":34},{"id":"2203.07559","title":"On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency","created":"2022-03-14","cited_by_count":31},{"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":"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":"2408.09773","title":"Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?","created":"2024-08-19","cited_by_count":23},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21},{"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":"2407.07950","title":"Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance","created":"2024-07-10","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":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13},{"id":"2503.13447","title":"MetaScale: Test-Time Scaling with Evolving Meta-Thoughts","created":"2025-03-17","cited_by_count":13},{"id":"2412.15479","title":"Continual Learning Using Only Large Language Model Prompting","created":"2024-12-20","cited_by_count":5},{"id":"2503.11381","title":"Modeling Subjectivity in Cognitive Appraisal with Language Models","created":"2025-03-14","cited_by_count":3},{"id":"2504.03975","title":"GREATERPROMPT: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization","created":"2025-04-04","cited_by_count":3}],"next_cursor":null}