Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions Jenny Kunz author Martin Jirenius author Oskar Holmström author Marco Kuhlmann author 2022-12 text Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP Jasmijn Bastings editor Yonatan Belinkov editor Yanai Elazar editor Dieuwke Hupkes editor Naomi Saphra editor Sarah Wiegreffe editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates (Hybrid) conference publication kunz-etal-2022-human 10.18653/v1/2022.blackboxnlp-1.14 https://aclanthology.org/2022.blackboxnlp-1.14/ 2022-12 164 177