{"total":23,"rows":[{"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,"area":null},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69,"area":null},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65,"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":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2407.16221","title":"Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models","created":"2024-07-23","cited_by_count":57,"area":null},{"id":"2402.00707","title":"Non-Exchangeable Conformal Language Generation with Nearest Neighbors","created":"2024-02-01","cited_by_count":21,"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":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2410.08793","title":"On the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2405.00632","title":"When Quantization Affects Confidence of Large Language Models?","created":"2024-05-01","cited_by_count":5,"area":null},{"id":"2407.02062","title":"Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2601.08064","title":"Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2502.01458","title":"The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2402.14184","title":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","created":"2024-02-22","cited_by_count":1,"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":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.22068","title":"Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2605.31220","title":"Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2404.05088","title":"How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2606.05654","title":"When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2610.04239","title":"Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}