{"total":71,"rows":[{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2405.01976","title":"Conformal Prediction for Natural Language Processing: A Survey","created":"2024-05-03","cited_by_count":53,"area":null},{"id":"2502.07068","title":"Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations","created":"2025-02-10","cited_by_count":53,"area":null},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"area":null},{"id":"2405.05860","title":"The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels","created":"2024-05-09","cited_by_count":38,"area":null},{"id":"2305.13788","title":"Can Large Language Models Capture Dissenting Human Voices?","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2405.01299","title":"The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation","created":"2024-05-02","cited_by_count":29,"area":null},{"id":"2504.11975","title":"SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes","created":"2025-04-16","cited_by_count":27,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22,"area":null},{"id":"2501.19047","title":"Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)","created":"2025-01-31","cited_by_count":20,"area":null},{"id":"2411.04852","title":"Conformalized Credal Regions for Classification with Ambiguous Ground Truth","created":"2024-11-07","cited_by_count":19,"area":null},{"id":"2404.15720","title":"Annotator-Centric Active Learning for Subjective NLP Tasks","created":"2024-04-24","cited_by_count":18,"area":null},{"id":"2311.05265","title":"Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels","created":"2023-11-09","cited_by_count":17,"area":null},{"id":"2406.17600","title":"\"Seeing the Big through the Small\": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2506.09796","title":"Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2304.04758","title":"Expectations over Unspoken Alternatives Predict Pragmatic Inferences","created":"2023-04-07","cited_by_count":9,"area":null},{"id":"2402.07214","title":"Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification","created":"2024-02-11","cited_by_count":9,"area":null},{"id":"2409.13879","title":"\"I Never Said That\": A dataset, taxonomy and baselines on response clarity classification","created":"2024-09-20","cited_by_count":9,"area":null},{"id":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2412.20309","title":"Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain","created":"2024-12-29","cited_by_count":9,"area":"rag"},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2307.02191","title":"Evaluating AI systems under uncertain ground truth: a case study in dermatology","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2410.02773","title":"Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA","created":"2024-09-17","cited_by_count":6,"area":"mllm"},{"id":"2304.12443","title":"Understanding and Predicting Human Label Variation in Natural Language Inference through Explanation","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2411.04421","title":"Variational Low-Rank Adaptation Using IVON","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2506.14280","title":"Improving LoRA with Variational Learning","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2603.14027","title":"SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2402.17527","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2409.09629","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2411.10080","title":"Understanding The Effect Of Temperature On Alignment With Human Opinions","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2505.23798","title":"Unveiling the \"Fairness Seesaw\": Discovering and Mitigating Gender and Race Bias in Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2604.27345","title":"LLMs Capture Emotion Labels, Not Emotion Uncertainty: Distributional Analysis and Calibration of Human-LLM Judgment Gaps","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2212.09409","title":"Aggregating Soft Labels from Crowd Annotations Improves Uncertainty Estimation Under Distribution Shift","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2404.04035","title":"A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2411.13760","title":"A Framework for Evaluating LLMs Under Task Indeterminacy","created":"2024-11-21","cited_by_count":3,"area":null},{"id":"2510.00263","title":"Judging with Confidence: Calibrating Autoraters to Preference Distributions","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2606.23357","title":"SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2510.13836","title":"SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2605.24773","title":"Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.05376","title":"SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2407.02138","title":"Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2412.04025","title":"Exploring the Influence of Label Aggregation on Minority Voices: Implications for Dataset Bias and Model Training","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2502.12225","title":"Subjective Logic Encodings","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.02072","title":"Express Your Doubts -- Probabilistic World Modeling Should not be Based on Token logprobs","created":"2025-05-04","cited_by_count":1,"area":"wm"},{"id":"2510.11295","title":"Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering","created":"2025-10-13","cited_by_count":1,"area":"mllm"},{"id":"2512.08646","title":"QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2603.22879","title":"Confidence Calibration under Ambiguous Ground Truth","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2509.17794","title":"Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.12036","title":"On the Interplay between Human Label Variation and Model Fairness","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2603.14092","title":"Soft Mean Expected Calibration Error (SMECE): A Calibration Metric for Probabilistic Labels","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.16654","title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.08452","title":"NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.18648","title":"An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.08961","title":"NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.02455","title":"Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.15619","title":"Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.06444","title":"Decomposing LLM-Judge Uncertainty to Target Expert Labels","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.26468","title":"How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.36689","title":"CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01006","title":"Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.10805","title":"Whose Ground Truth? Embracing Ambiguity in Human-Centered AI","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}