Are Shortest Rationales the Best Explanations for Human Understanding?

Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao Huang


Abstract
Existing self-explaining models typically favor extracting the shortest possible rationales — snippets of an input text “responsible for” corresponding output — to explain the model prediction, with the assumption that shorter rationales are more intuitive to humans. However, this assumption has yet to be validated. Is the shortest rationale indeed the most human-understandable? To answer this question, we design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end-task performance and human-annotated rationale agreement, making it a suitable representation of the recent class of self-explaining models. We use LimitedInk to conduct a user study on the impact of rationale length, where we ask human judges to predict the sentiment label of documents based only on LimitedInk-generated rationales with different lengths. We show rationales that are too short do not help humans predict labels better than randomly masked text, suggesting the need for more careful design of the best human rationales.
Anthology ID:
2022.acl-short.2
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10–19
Language:
URL:
https://aclanthology.org/2022.acl-short.2
DOI:
10.18653/v1/2022.acl-short.2
Bibkey:
Cite (ACL):
Hua Shen, Tongshuang Wu, Wenbo Guo, and Ting-Hao Huang. 2022. Are Shortest Rationales the Best Explanations for Human Understanding?. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 10–19, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Are Shortest Rationales the Best Explanations for Human Understanding? (Shen et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.2.pdf
Code
 huashen218/limitedink