Investigating the Benefits of Free-Form Rationales

Jiao Sun, Swabha Swayamdipta, Jonathan May, Xuezhe Ma


Abstract
Free-form rationales aim to aid model interpretability by supplying the background knowledge that can help understand model decisions. Crowdsourced rationales are provided for commonsense QA instances in popular datasets such as CoS-E and ECQA, but their utility remains under-investigated. We present human studies which show that ECQA rationales indeed provide additional background information to understand a decision, while over 88% of CoS-E rationales do not. Inspired by this finding, we ask: can the additional context provided by free-form rationales benefit models, similar to human users? We investigate the utility of rationales as an additional source of supervision, by varying the quantity and quality of rationales during training. After controlling for instances where rationales leak the correct answer while not providing additional background knowledge, we find that incorporating only 5% of rationales during training can boost model performance by 47.22% for CoS-E and 57.14% for ECQA during inference. Moreover, we also show that rationale quality matters: compared to crowdsourced rationales, T5-generated rationales provide not only weaker supervision to models, but are also not helpful for humans in aiding model interpretability.
Anthology ID:
2022.findings-emnlp.432
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5867–5882
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.432
DOI:
10.18653/v1/2022.findings-emnlp.432
Bibkey:
Cite (ACL):
Jiao Sun, Swabha Swayamdipta, Jonathan May, and Xuezhe Ma. 2022. Investigating the Benefits of Free-Form Rationales. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5867–5882, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Investigating the Benefits of Free-Form Rationales (Sun et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.432.pdf