Active Example Selection For In-context Learning

Yiming Zhang, Shi Feng, Chenhao Tan. Arxiv 2022

[Paper]    
Agentic Fine Tuning GPT In Context Learning Merging Model Architecture Pretraining Methods Prompting RAG Reinforcement Learning Training Techniques

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a \(5.8%\) improvement on average. Examples selected from our learned policies can even achieve a small improvement on GPT-3 Ada. However, the improvement diminishes on larger GPT-3 models, suggesting emerging capabilities of large language models.

Similar Work