{"total":28,"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":"2309.07034","title":"Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting","created":"2023-09-13","cited_by_count":81,"area":null},{"id":"2410.07991","title":"Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets","created":"2024-10-10","cited_by_count":31,"area":null},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2605.29800","title":"Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels","created":"2026-05-28","cited_by_count":26,"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":"2601.09065","title":"Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP","created":"2026-01-14","cited_by_count":13,"area":null},{"id":"2410.08820","title":"Which Demographics do LLMs Default to During Annotation?","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2407.14259","title":"Voices in a Crowd: Searching for Clusters of Unique Perspectives","created":"2024-07-19","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":"2502.01891","title":"Training and Evaluating with Human Label Variation: An Empirical Study","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2504.19622","title":"From Evidence to Belief: A Bayesian Epistemology Approach to Language Models","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2409.09045","title":"United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections","created":"2024-08-29","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":"2410.03429","title":"How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics","created":"2024-10-04","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":"2412.11745","title":"Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detection","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.00489","title":"Embracing Diversity: A Multi-Perspective Approach with Soft Labels","created":"2025-03-01","cited_by_count":3,"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":"2404.06670","title":"What's Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2405.02937","title":"Unraveling the Dominance of Large Language Models Over Transformer Models for Bangla Natural Language Inference: A Comprehensive Study","created":"2024-05-05","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2506.23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2407.09688","title":"Large Language Models for Integrating Social Determinant of Health Data: A Case Study on Heart Failure 30-Day Readmission Prediction","created":"2024-07-12","cited_by_count":0,"area":null},{"id":"2411.18162","title":"SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment","created":"2024-11-27","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":"2607.00873","title":"How Ethos and Pathos Appeals Resonate in Reader Interpretations of Social Media Messages","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.35302","title":"Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}