{"total":19,"rows":[{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2212.12672","title":"Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text","created":"2022-12-24","cited_by_count":63,"area":null},{"id":"2301.09790","title":"The Next Chapter: A Study of Large Language Models in Storytelling","created":"2023-01-24","cited_by_count":58,"area":null},{"id":"2407.11484","title":"The Oscars of AI Theater: A Survey on Role-Playing with Language Models","created":"2024-07-16","cited_by_count":48,"area":null},{"id":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"area":null},{"id":"2305.14770","title":"Using Natural Language Explanations to Rescale Human Judgments","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2411.12719","title":"Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2406.12645","title":"Evaluating Evidence Attribution in Generated Fact Checking Explanations","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2603.13683","title":"Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2407.01878","title":"Compare without Despair: Reliable Preference Evaluation with Generation Separability","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2502.09532","title":"Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2512.08936","title":"A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellness","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2403.15278","title":"Specifying Genericity through Inclusiveness and Abstractness Continuous Scales","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2506.23527","title":"On Recipe Memorization and Creativity in Large Language Models: Is Your Model a Creative Cook, a Bad Cook, or Merely a Plagiator?","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2507.19117","title":"Objectifying the Subjective: Cognitive Biases in Topic Interpretations","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2512.09292","title":"Identifying Bias in Machine-generated Text Detection","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2603.23433","title":"Mecha-nudges for Machines","created":"2026-03-24","cited_by_count":0,"area":null}],"next_cursor":null}