Explanation-based Finetuning Makes Models More Robust to Spurious Cues

Josh Magnus Ludan, Yixuan Meng, Tai Nguyen, Saurabh Shah, Qing Lyu, Marianna Apidianaki, Chris Callison-Burch


Abstract
Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based finetuning as a general approach to mitigate LLMs’ reliance on spurious correlations. Unlike standard finetuning where the model only predicts the answer given the input, we finetune the model to additionally generate a free-text explanation supporting its answer. To evaluate our method, we finetune the model on artificially constructed training sets containing different types of spurious cues, and test it on a test set without these cues. Compared to standard finetuning, our method makes GPT-3 (davinci) remarkably more robust against spurious cues in terms of accuracy drop across four classification tasks: ComVE (+1.2), CREAK (+9.1), e-SNLI (+15.4), and SBIC (+6.5). The efficacy generalizes across multiple model families and scales, with greater gains for larger models. Finally, our method also works well with explanations generated by the model, implying its applicability to more datasets without human-written explanations.
Anthology ID:
2023.acl-long.242
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4420–4441
Language:
URL:
https://aclanthology.org/2023.acl-long.242
DOI:
10.18653/v1/2023.acl-long.242
Bibkey:
Cite (ACL):
Josh Magnus Ludan, Yixuan Meng, Tai Nguyen, Saurabh Shah, Qing Lyu, Marianna Apidianaki, and Chris Callison-Burch. 2023. Explanation-based Finetuning Makes Models More Robust to Spurious Cues. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4420–4441, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Explanation-based Finetuning Makes Models More Robust to Spurious Cues (Ludan et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.242.pdf
Video:
 https://aclanthology.org/2023.acl-long.242.mp4