Test-time Corpus Feedback: From Retrieval to RAG

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rathee, Mandeep, Venktesh, V, MacAvaney, Sean, Anand, Avishek
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911118479327232
author Rathee, Mandeep
Venktesh, V
MacAvaney, Sean
Anand, Avishek
author_facet Rathee, Mandeep
Venktesh, V
MacAvaney, Sean
Anand, Avishek
contents Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines continue to treat retrieval and reasoning as isolated components, retrieving documents once and then generating answers without further interaction. This static design often limits performance on complex tasks that require iterative evidence gathering or high-precision retrieval. Recent work in both the information retrieval (IR) and NLP communities has begun to close this gap by introducing adaptive retrieval and ranking methods that incorporate feedback. In this survey, we present a structured overview of advanced retrieval and ranking mechanisms that integrate such feedback. We categorize feedback signals based on their source and role in improving the query, retrieved context, or document pool. By consolidating these developments, we aim to bridge IR and NLP perspectives and highlight retrieval as a dynamic, learnable component of end-to-end RAG systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15437
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test-time Corpus Feedback: From Retrieval to RAG
Rathee, Mandeep
Venktesh, V
MacAvaney, Sean
Anand, Avishek
Information Retrieval
Artificial Intelligence
Machine Learning
Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines continue to treat retrieval and reasoning as isolated components, retrieving documents once and then generating answers without further interaction. This static design often limits performance on complex tasks that require iterative evidence gathering or high-precision retrieval. Recent work in both the information retrieval (IR) and NLP communities has begun to close this gap by introducing adaptive retrieval and ranking methods that incorporate feedback. In this survey, we present a structured overview of advanced retrieval and ranking mechanisms that integrate such feedback. We categorize feedback signals based on their source and role in improving the query, retrieved context, or document pool. By consolidating these developments, we aim to bridge IR and NLP perspectives and highlight retrieval as a dynamic, learnable component of end-to-end RAG systems.
title Test-time Corpus Feedback: From Retrieval to RAG
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.15437