English

UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation

Computation and Language 2025-05-27 v3

Abstract

In-context learning (ICL) enhances the reasoning abilities of Large Language Models (LLMs) by prepending a few demonstrations. It motivates researchers to introduce more examples to provide additional contextual information for the generation. However, existing methods show a significant limitation due to the problem of excessive growth in context length, which causes a large hardware burden. In addition, shallow-relevant examples selected by off-the-shelf tools hinder LLMs from capturing useful contextual information for generation. In this paper, we propose \textbf{UniICL}, a novel \textbf{Uni}fied \textbf{ICL} framework that unifies demonstration compression, demonstration selection, and final response generation. Furthermore, to boost inference efficiency, we design a tailored compression strategy that allows UniICL to cache compression results into \textbf{Demonstration Bank} (\textbf{DB}), which avoids repeated compression of the same demonstration. Extensive out-of-domain evaluations prove the advantages of UniICL in both effectiveness and efficiency.

Keywords

Cite

@article{arxiv.2405.17062,
  title  = {UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation},
  author = {Jun Gao and Qi Lv and Zili Wang and Tianxiang Wu and Ziqiang Cao and Wenjie Li},
  journal= {arXiv preprint arXiv:2405.17062},
  year   = {2025}
}

Comments

ACL2025

R2 v1 2026-06-28T16:41:48.755Z