{"total":12,"rows":[{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"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":"2505.23785","title":"Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale","created":"2025-05-23","cited_by_count":10,"area":null},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2510.12817","title":"From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2411.15387","title":"From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2511.21912","title":"Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2609.32382","title":"PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}