Complementary Explanations for Effective In-Context Learning

Xi Ye, Srinivasan Iyer, Asli Celikyilmaz, Veselin Stoyanov, Greg Durrett, Ramakanth Pasunuru


Abstract
Large language models (LLMs) have exhibited remarkable capabilities in learning from expla- nations in prompts, but there has been limited understanding of exactly how these explana- tions function or why they are effective. This work aims to better understand the mechanisms by which explanations are used for in-context learning. We first study the impact of two dif- ferent factors on the performance of prompts with explanations: the computation trace (the way the solution is decomposed) and the natural language used to express the prompt. By per- turbing explanations on three controlled tasks, we show that both factors contribute to the ef- fectiveness of explanations. We further study how to form maximally effective sets of expla- nations for solving a given test query. We find that LLMs can benefit from the complemen- tarity of the explanation set: diverse reasoning skills shown by different exemplars can lead to better performance. Therefore, we propose a maximal marginal relevance-based exemplar selection approach for constructing exemplar sets that are both relevant as well as comple- mentary, which successfully improves the in- context learning performance across three real- world tasks on multiple LLMs.
Anthology ID:
2023.findings-acl.273
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4469–4484
Language:
URL:
https://aclanthology.org/2023.findings-acl.273
DOI:
10.18653/v1/2023.findings-acl.273
Bibkey:
Cite (ACL):
Xi Ye, Srinivasan Iyer, Asli Celikyilmaz, Veselin Stoyanov, Greg Durrett, and Ramakanth Pasunuru. 2023. Complementary Explanations for Effective In-Context Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4469–4484, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Complementary Explanations for Effective In-Context Learning (Ye et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-acl.273.pdf