# Feedback Adaptation for Retrieval-Augmented Generation

Source: [Feedback Adaptation for Retrieval-Augmented Generation](<https://www.sota2.com/research/paper/69d732af7d0172140ec76c58>)

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

Data updated: 2026-04-18T05:00:04.772Z

Authors: Jihwan Bang, Seunghan Yang, Kyuhong Shim, Simyung Chang, Juntae Lee, Sungha Choi

Published: 2026-04-08T03:47:48.000Z

## Abstract

Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and fail to capture how systems adapt after feedback is introduced. We introduce feedback adaptation as a problem setting for RAG systems, which asks how effectively and how quickly corrective feedback propagates to future queries. To make this behavior measurable, we propose two evaluation axes: correction lag, which captures the delay between feedback provision and behavioral change, and post-feedback performance, which measures reliability on semantically related queries after feedback. Using these metrics, we show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation. We further propose PatchRAG, a minimal inference-time instantiation that incorporates feedback without retraining, demonstrating immediate correction and strong post-feedback generalization under the proposed evaluation. Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.

## 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.

- [Question Answering on Natural Questions (NQ) (EM and Performance Gain Metrics)](<https://www.sota2.com/research/sota/question-answering-on-natural-questions-nq-em-and-performance-gain-metrics.md>): Question Answering; Natural Questions (NQ); Exact Match (EM): 49.8.

- [Question Answering on TriviaQA (EM, Performance Gain)](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-performance-gain.md>): Question Answering; TriviaQA; Exact Match (EM): 83.9.

- [Question Answering on HotpotQA (F1, Performance Gain)](<https://www.sota2.com/research/sota/question-answering-on-hotpotqa-f1-performance-gain.md>): Question Answering; HotpotQA; F1 Score: 53.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.06647>)

[PDF](<https://arxiv.org/pdf/2604.06647.pdf>)