How Do In-Context Examples Affect Compositional Generalization?
Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, Dongmei Zhang
Abstract
Compositional generalization–understanding unseen combinations of seen primitives–is an essential reasoning capability in human intelligence. The AI community mainly studies this capability by fine-tuning neural networks on lots of training samples, while it is still unclear whether and how in-context learning–the prevailing few-shot paradigm based on large language models–exhibits compositional generalization. In this paper, we present CoFe, a test suite to investigate in-context compositional generalization. We find that the compositional generalization performance can be easily affected by the selection of in-context examples, thus raising the research question what the key factors are to make good in-context examples for compositional generalization. We study three potential factors: similarity, diversity and complexity. Our systematic experiments indicate that in-context examples should be structurally similar to the test case, diverse from each other, and individually simple. Furthermore, two strong limitations are observed: in-context compositional generalization on fictional words is much weaker than that on commonly used ones; it is still critical that the in-context examples should cover required linguistic structures, even though the backbone model has been pre-trained on large corpus. We hope our analysis would facilitate the understanding and utilization of in-context learning paradigm.- Anthology ID:
- 2023.acl-long.618
- 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:
- 11027–11052
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.618
- DOI:
- 10.18653/v1/2023.acl-long.618
- Cite (ACL):
- Shengnan An, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Jian-Guang Lou, and Dongmei Zhang. 2023. How Do In-Context Examples Affect Compositional Generalization?. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11027–11052, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- How Do In-Context Examples Affect Compositional Generalization? (An et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.acl-long.618.pdf