# Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents

> Research article (Proceedings of the 4th Workshop on NLP for Conversational AI, 2022) · cited 35× · AI/ML

**Wikidata**: [openalex:W4285188834](https://www.wikidata.org/wiki/openalex:W4285188834)  
**Source**: https://4ort.xyz/entity/human-evaluation-of-conversations-is-an-open-problem-comparing-the-sensitivity-of-various-methods-for-evaluating-dialogu