Abstract
Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the quality of the selected examples. In this paper, we propose a novel framework to iteratively train dense retrievers that can identify high-quality in-context examples for LLMs. Our framework initially trains a reward model based on LLM feedback to evaluate the quality of candidate examples, followed by knowledge distillation to train a bi-encoder based dense retriever. Our experiments on a suite of 30 tasks demonstrate that our framework significantly enhances in-context learning performance. Furthermore, we show the generalization ability of our framework to unseen tasks during training. An in-depth analysis reveals that our model improves performance by retrieving examples with similar patterns, and the gains are consistent across LLMs of varying sizes.- Anthology ID:
- 2024.eacl-long.105
- Volume:
- Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julian’s, Malta
- Editors:
- Yvette Graham, Matthew Purver
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1752–1767
- Language:
- URL:
- https://aclanthology.org/2024.eacl-long.105
- DOI:
- Cite (ACL):
- Liang Wang, Nan Yang, and Furu Wei. 2024. Learning to Retrieve In-Context Examples for Large Language Models. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1752–1767, St. Julian’s, Malta. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Retrieve In-Context Examples for Large Language Models (Wang et al., EACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.eacl-long.105.pdf