Nothing Special   »   [go: up one dir, main page]

Skill-Based Few-Shot Selection for In-Context Learning

Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou


Abstract
*In-context learning* is the paradigm that adapts large language models to downstream tasks by providing a few examples. *Few-shot selection*—selecting appropriate examples for each test instance separately—is important for in-context learning. In this paper, we propose **Skill-KNN**, a skill-based few-shot selection method for in-context learning. The key advantages of Skill-KNN include: (1) it addresses the problem that existing methods based on pre-trained embeddings can be easily biased by surface natural language features that are not important for the target task; (2) it does not require training or fine-tuning of any models, making it suitable for frequently expanding or changing example banks. The key insight is to optimize the inputs fed into the embedding model, rather than tuning the model itself. Technically, Skill-KNN generates the skill-based descriptions for each test case and candidate example by utilizing a pre-processing few-shot prompting, thus eliminating unimportant surface features. Experimental results across five cross-domain semantic parsing datasets and six backbone models show that Skill-KNN significantly outperforms existing methods.
Anthology ID:
2023.emnlp-main.831
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13472–13492
Language:
URL:
https://aclanthology.org/2023.emnlp-main.831
DOI:
10.18653/v1/2023.emnlp-main.831
Bibkey:
Cite (ACL):
Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, and Jian-Guang Lou. 2023. Skill-Based Few-Shot Selection for In-Context Learning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13472–13492, Singapore. Association for Computational Linguistics.
Cite (Informal):
Skill-Based Few-Shot Selection for In-Context Learning (An et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.831.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.831.mp4