GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks

arXiv:2311.09606v2 Announce Type: replace
Abstract: In-context Learning (ICL) is the ability of Large Language Models (LLMs) to perform new tasks when conditioned on prompts comprising a few task examples. However, ICL performance can be critically sensitive to the choice of examples. To dynamically select the best examples for every test input, we propose Example Gisting, a novel approach for training example encoders through supervised fine-tuning with an attention bottleneck between the inputs and outputs. These gist models form the basis …

abstract arxiv bottlenecks context cs.cl every example examples in-context learning language language models large language large language models llms performance prompts tasks type