# Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

Source: [Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering](<https://www.sota2.com/research/paper/68fa6fc11e209131cea4741a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-24T19:25:47.621Z

Authors: Hai Ye, Qizhe Xie, Hwee Tou Ng

Published: 2023-06-11T21:18:50.000Z

## Abstract

In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast the problem as a stochastic decision-making process, aiming to determine the best adapted model after adaptation. We discuss two frameworks: multi-armed bandit learning and multi-armed dueling bandits. Compared to multi-armed bandit learning, the dueling framework allows pairwise collaboration among K models, which is solved by a novel method named Co-UCB proposed in this work. Experiments on six datasets of extractive question answering (QA) show that the dueling framework using Co-UCB is more effective than other strong baselines for our studied problem.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.06779>)

[PDF](<https://arxiv.org/pdf/2306.06779.pdf>)

[Implementation](<https://github.com/oceanypt/Multi-source-TTA>)