{"total":15,"rows":[{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2203.05899","title":"Achieving Reliable Human Assessment of Open-Domain Dialogue Systems","created":"2022-03-11","cited_by_count":31,"area":null},{"id":"2106.06132","title":"TellMeWhy: A Dataset for Answering Why-Questions in Narratives","created":"2021-06-11","cited_by_count":27,"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":"2109.09195","title":"Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries","created":"2021-09-19","cited_by_count":15,"area":null},{"id":"2101.11298","title":"How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2105.11197","title":"Towards Standard Criteria for human evaluation of Chatbots: A Survey","created":"2021-05-24","cited_by_count":6,"area":null},{"id":"2108.08102","title":"Affective Decoding for Empathetic Response Generation","created":"2021-08-18","cited_by_count":4,"area":null},{"id":"2210.13025","title":"On the Effectiveness of Automated Metrics for Text Generation Systems","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2112.08048","title":"Dynamic Human Evaluation for Relative Model Comparisons","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2408.09765","title":"Baby Bear: Seeking a Just Right Rating Scale for Scalar Annotations","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2407.11857","title":"Evaluating Task-Oriented Dialogue Consistency through Constraint Satisfaction","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2607.09338","title":"Towards Detecting Inconsistencies in End-to-end Generated TODs","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}