MILE: A Mutation Testing Framework of In-Context Learning Systems

In-context Learning (ICL) has achieved notable success in the applications of large language models (LLMs). By adding only a few input-output pairs that demonstrate a new task, the LLM can efficiently learn the task during inference without modifying the model parameters. Such mysterious ability of...

Full description

Saved in:
Bibliographic Details
Main Authors Wei, Zeming, Zhang, Yihao, Sun, Meng
Format Journal Article
LanguageEnglish
Published 07.09.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Cryptography and Security
Computer Science - Learning
Computer Science - Software Engineering
Online AccessGet full text

Cover

More Information
Summary:In-context Learning (ICL) has achieved notable success in the applications of large language models (LLMs). By adding only a few input-output pairs that demonstrate a new task, the LLM can efficiently learn the task during inference without modifying the model parameters. Such mysterious ability of LLMs has attracted great research interests in understanding, formatting, and improving the in-context demonstrations, while still suffering from drawbacks like black-box mechanisms and sensitivity against the selection of examples. In this work, inspired by the foundations of adopting testing techniques in machine learning (ML) systems, we propose a mutation testing framework designed to characterize the quality and effectiveness of test data for ICL systems. First, we propose several mutation operators specialized for ICL demonstrations, as well as corresponding mutation scores for ICL test sets. With comprehensive experiments, we showcase the effectiveness of our framework in evaluating the reliability and quality of ICL test suites. Our code is available at https://github.com/weizeming/MILE.
DOI:10.48550/arxiv.2409.04831