FLamE: Few-shot Learning from Natural Language Explanations

Yangqiaoyu Zhou, Yiming Zhang, Chenhao Tan


Abstract
Natural language explanations have the potential to provide rich information that in principle guides model reasoning. Yet, recent work by Lampinen et al. has shown limited utility of natural language explanations in improving classification. To effectively learn from explanations, we present FLamE, a two-stage few-shot learning framework that first generates explanations using GPT-3, and then fine-tunes a smaller model (e.g., RoBERTa) with generated explanations. Our experiments on natural language inference demonstrate effectiveness over strong baselines, increasing accuracy by 17.6% over GPT-3 Babbage and 5.7% over GPT-3 Davinci in e-SNLI.Despite improving classification performance, human evaluation surprisingly reveals that the majority of generated explanations does not adequately justify classification decisions. Additional analyses point to the important role of label-specific cues (e.g., “not know” for the neutral label) in generated explanations.
Anthology ID:
2023.acl-long.372
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:
6743–6763
Language:
URL:
https://aclanthology.org/2023.acl-long.372
DOI:
10.18653/v1/2023.acl-long.372
Bibkey:
Cite (ACL):
Yangqiaoyu Zhou, Yiming Zhang, and Chenhao Tan. 2023. FLamE: Few-shot Learning from Natural Language Explanations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6743–6763, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
FLamE: Few-shot Learning from Natural Language Explanations (Zhou et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.372.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.372.mp4