# Simulating Bandit Learning from User Feedback for Extractive Question Answering

Source: [Simulating Bandit Learning from User Feedback for Extractive Question Answering](<https://www.sota2.com/research/paper/68fa6c121e209131cea31ef3>)

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

Data updated: 2025-12-24T16:45:24.978Z

Authors: Ge Gao, Eunsol Choi, Yoav Artzi

Published: 2022-03-18T17:47:58.000Z

## Abstract

We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning scenarios with focus on reducing data annotation. We show that systems initially trained on a small number of examples can dramatically improve given feedback from users on model-predicted answers, and that one can use existing datasets to deploy systems in new domains without any annotation, but instead improving the system on-the-fly via user feedback.

## 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/2203.10079>)

[PDF](<https://arxiv.org/pdf/2203.10079.pdf>)