Skill-Based Few-Shot Selection for In-Context Learning
This addresses the challenge of few-shot selection for in-context learning, which is crucial for adapting models to tasks without training, but it is incremental as it builds on existing embedding-based methods.
The paper tackles the problem of selecting appropriate examples for in-context learning in large language models, proposing Skill-KNN to reduce bias from surface features and showing it significantly outperforms existing methods across five datasets and six models.
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.