{"total":17,"rows":[{"id":"2402.01383","title":"LLM-based NLG Evaluation: Current Status and Challenges","created":"2024-02-02","cited_by_count":73,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2407.01119","title":"Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?","created":"2024-07-01","cited_by_count":27,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2211.05044","title":"What is Wrong with Language Models that Can Not Tell a Story?","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2311.02049","title":"Post Turing: Mapping the landscape of LLM Evaluation","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2405.12438","title":"CoCo Matrix: Taxonomy of Cognitive Contributions in Co-writing with Intelligent Agents","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2505.04654","title":"A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2212.02170","title":"Automatic Generation of Factual News Headlines in Finnish","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2212.02911","title":"Modern French Poetry Generation with RoBERTa and GPT-2","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2409.01053","title":"A Perspective on Literary Metaphor in the Context of Generative AI","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2310.20326","title":"Erato: Automatizing Poetry Evaluation","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2512.15183","title":"From NLG Evaluation to Modern Student Assessment in the Era of ChatGPT: The Great Misalignment Problem and Pedagogical Multi-Factor Assessment (P-MFA)","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2604.22517","title":"Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.10853","title":"Grounded Satirical Generation with RAG","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":null}