Papers
arxiv:2507.04221

Context Tuning for In-Context Optimization

Published on Jul 6
Authors:
,
,
,

Abstract

Context Tuning enhances few-shot language model adaptation by initializing prompts with task-specific examples, improving performance and efficiency over traditional methods.

AI-generated summary

We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of language models (LLMs) without fine-tuning model parameters. While prompt-based adaptation techniques have demonstrated the effectiveness of lightweight adaptation methods for large language models (LLMs), they typically initialize a trainable prompt or prefix with irrelevant tokens for the task at hand. In contrast, Context Tuning initializes the trainable prompt or prefix with task-specific demonstration examples, leveraging the model's inherent In-Context Learning (ICL) ability to extract relevant information for improved few-shot learning performance. Extensive evaluations on benchmarks such as CrossFit, UnifiedQA, MMLU, BIG-Bench Hard, and ARC demonstrate that Context Tuning outperforms traditional prompt-based adaptation methods and achieves competitive accuracy to Test-Time Training with significantly higher training efficiency.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.04221 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.04221 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.04221 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.