Context Attribution with Multi-Armed Bandit Optimization

TL;DR

This paper introduces a new method for attributing the influence of context segments on language model outputs using multi-armed bandit optimization, reducing query costs while maintaining attribution quality.

Contribution

It formulates context attribution as a combinatorial multi-armed bandit problem and employs Linear Thompson Sampling for efficient, adaptive identification of influential context segments.

Findings

Achieves up to 30% reduction in model queries.

Matches or exceeds existing attribution methods in quality.

Applicable to both open-source and API-based models.

Abstract

Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy retrieval-augmented generation. We propose a novel framework that formulates context attribution as a combinatorial multi-armed bandit problem. We utilize Linear Thompson Sampling to efficiently identify the most influential context segments while minimizing the number of model queries. Our reward function leverages token log-probabilities to measure how well a subset of segments supports the original response, making it applicable to both open-source and black-box API-based models. Unlike SHAP and other perturbation-based methods that sample subsets uniformly, our approach adaptively prioritizes informative subsets based on posterior estimates of segment relevance, reducing computational costs. Experiments on multiple QA benchmarks demonstrate that our method achieves up to 30\% reduction in model queries while matching or exceeding the attribution quality of existing approaches. Our code is publicly available at https://github.com/pd90506/camab.