Feedback Adaptation for Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2604.06647v2
• Date: Thu, 16 Apr 2026 01:52:50 GMT
• Title: Feedback Adaptation for Retrieval-Augmented Generation
• Abstract summary: We introduce feedback adaptation as a problem setting for RAG systems.<n>We show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation.<n>Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.
• Score: 36.004563021329965
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• User Feedback Provides a Unique Signal that LLMs Can not Detect [25.849928795741672]
  We demonstrate that user feedback is a highly actionable signal for improvement.<n>We show that feedback-informed revisions resolve targeted issues at significantly higher rates than baseline revisions.
  arXiv  Detail & Related papers  (2026-09-02T17:42:44Z)
• CAFE: Self-Improving Search Agents Need Co-Evolving Feedback [64.5257526832476]
  Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound.<n>Treating corrective feedback as a learned in-trajectory intervention couples the two roles: the agent must decide when to request and use feedback, while the critic must infer useful corrections from outcome-confounded rollouts whose failure patterns shift as the agent improves.
  arXiv  Detail & Related papers  (2026-08-25T16:39:00Z)
• Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making [0.16385815610837165]
  Utility-Augmented Transformer is a new feedback-conditioned retrieval attention architecture.<n>We show that UAT consistently improves performance over observation-only, test-time adaptation, and input-level feedback baselines.
  arXiv  Detail & Related papers  (2026-07-21T09:52:23Z)
• TRAFA: Anticipating User Actions to Reduce Errors in Procedural Tasks with Predictive Feedback [20.81220736856844]
  We present TRAFA, a real-time predictive feedback system for procedural tasks.<n> TRAFA operationalizes predictive feedback through a Track-Forecast-Act framework.<n>Results show that predictive feedback improves task accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-05-23T11:29:15Z)
• Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents [6.158612515104146]
  We introduce Helpfulness-Harmfulness metrics to measure the tradeoff between agent feedback and reviewer feedback.<n>We evaluate our approach on BFCL and Tau2-Bench (multi-turn stateful scenarios), achieving +5.5% on irrelevance detection and +7.1% on multi-turn tasks.<n>Our metrics reveal that reviewer model choice is critical: the reasoning model o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o.
  arXiv  Detail & Related papers  (2026-04-29T22:09:47Z)
• The Diversity Paradox revisited: Systemic Effects of Feedback Loops in Recommender Systems [1.6167794587866464]
  We propose a feedback-loop model that captures implicit feedback, periodic retraining, and probabilistic adoption of recommendations.<n>We apply the framework on online retail and music streaming data and analyze systemic effects of the feedback loop.<n>Our results highlight the need to move beyond static evaluations and account explicitly for feedback-loop dynamics when designing recommender systems.
  arXiv  Detail & Related papers  (2026-02-18T09:52:52Z)
• On the Role of Feedback in Test-Time Scaling of Agentic AI Workflows [71.92083784393418]
  Agentic AI (systems that autonomously plan and act) are becoming widespread, yet their task success rate on complex tasks remains low.<n>Inference-time alignment relies on three components: sampling, evaluation, and feedback.<n>We introduce Iterative Agent Decoding (IAD), a procedure that repeatedly inserts feedback extracted from different forms of critiques.
  arXiv  Detail & Related papers  (2025-04-02T17:40:47Z)
• Enhancing Relation Extraction via Supervised Rationale Verification and Feedback [12.687458877141934]
  We propose a novel automated feedback framework for relation extraction.<n>It presents a rationale supervisor to verify the rationale and provides re-selected demonstrations as feedback to correct the initial prediction.<n>Our proposed framework significantly outperforms existing methods.
  arXiv  Detail & Related papers  (2024-12-10T08:18:29Z)
• Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data [34.55109747972333]
  This paper aims to adapt the source model to the target environment using user feedback readily available in real-world applications. We analyze this phenomenon via a novel concept called Negatively Biased Feedback (NBF) We propose a scalable adapting approach, Retrieval Latent Defending.
  arXiv  Detail & Related papers  (2024-07-22T05:15:41Z)
• Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs [57.16442740983528]
  In ad-hoc retrieval, evaluation relies heavily on user actions, including implicit feedback. The role of user feedback in annotators' assessment of turns in a conversational perception has been little studied. We focus on how the evaluation of task-oriented dialogue systems ( TDSs) is affected by considering user feedback, explicit or implicit, as provided through the follow-up utterance of a turn being evaluated.
  arXiv  Detail & Related papers  (2024-04-19T16:45:50Z)
• Exploiting Correlated Auxiliary Feedback in Parameterized Bandits [56.84649080789685]
  We study a novel variant of the parameterized bandits problem in which the learner can observe additional auxiliary feedback that is correlated with the observed reward. The auxiliary feedback is readily available in many real-life applications, e.g., an online platform that wants to recommend the best-rated services to its users can observe the user's rating of service (rewards) and collect additional information like service delivery time (auxiliary feedback)
  arXiv  Detail & Related papers  (2023-11-05T17:27:06Z)
• Breaking Feedback Loops in Recommender Systems with Causal Inference [99.22185950608838]
  Recent work has shown that feedback loops may compromise recommendation quality and homogenize user behavior. We propose the Causal Adjustment for Feedback Loops (CAFL), an algorithm that provably breaks feedback loops using causal inference. We show that CAFL improves recommendation quality when compared to prior correction methods.
  arXiv  Detail & Related papers  (2022-07-04T17:58:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.