{"total":25,"rows":[{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2410.11745","title":"Personas with Attitudes: Controlling LLMs for Diverse Data Annotation","created":"2024-10-15","cited_by_count":21,"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":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2411.17637","title":"On Limitations of LLM as Annotator for Low Resource Languages","created":"2024-11-26","cited_by_count":12,"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":"2411.10080","title":"Understanding The Effect Of Temperature On Alignment With Human Opinions","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2506.12468","title":"Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2507.02593","title":"Revisiting Active Learning under (Human) Label Variation","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"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":"2508.15239","title":"WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2508.17164","title":"The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum","created":"2025-08-23","cited_by_count":3,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2502.06004","title":"Analysis of LLM as a grammatical feature tagger for African American English","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2502.04997","title":"Aligning Black-box Language Models with Human Judgments","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2503.18253","title":"Enhancing Multi-Label Emotion Analysis and Corresponding Intensities for Ethiopian Languages","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2502.07186","title":"PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2508.09832","title":"Exploring the Potential of Large Language Models in Fine-Grained Review Comment Classification","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.24337","title":"Generative Large Language Models (gLLMs) in Content Analysis: A Practical Guide for Communication Research","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2605.13412","title":"LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.02911","title":"The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.30827","title":"Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.17291","title":"Extracting ontology-compliant knowledge from scientific text describing irradiated materials using large language models","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}