{"total":24,"rows":[{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"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":"2201.04723","title":"Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents","created":"2022-01-12","cited_by_count":62,"area":null},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59,"area":null},{"id":"2110.10746","title":"Better than Average: Paired Evaluation of NLP Systems","created":"2021-10-20","cited_by_count":30,"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":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2106.02228","title":"Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency","created":"2021-06-04","cited_by_count":12,"area":null},{"id":"2304.05253","title":"Approximating Online Human Evaluation of Social Chatbots with Prompting","created":"2023-04-11","cited_by_count":11,"area":null},{"id":"2212.09180","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","created":"2022-12-18","cited_by_count":9,"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":"2205.00965","title":"State-of-the-art in Open-domain Conversational AI: A Survey","created":"2022-05-02","cited_by_count":5,"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":"2305.14757","title":"Psychological Metrics for Dialog System Evaluation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2409.00262","title":"DiverseDialogue: A Methodology for Designing Chatbots with Human-Like Diversity","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2406.01131","title":"Favi-Score: A Measure for Favoritism in Automated Preference Ratings for Generative AI Evaluation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2104.10661","title":"Towards Automated Psychotherapy via Language Modeling","created":"2021-04-05","cited_by_count":1,"area":null},{"id":"2211.10596","title":"Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2203.03168","title":"Towards Robust Online Dialogue Response Generation","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2310.16319","title":"DiQAD: A Benchmark Dataset for End-to-End Open-domain Dialogue Assessment","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2411.00034","title":"Is Our Chatbot Telling Lies? Assessing Correctness of an LLM-based Dutch Support Chatbot","created":"2024-10-29","cited_by_count":0,"area":null}],"next_cursor":null}