Graph-Guided Passage Retrieval for Author-Centric Structured Feedback

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chitale, Maitreya Prafulla, Shetye, Ketaki Mangesh, Gupta, Harshit, Chaudhary, Manav, Shrivastava, Manish, Varma, Vasudeva
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908754344148992
author Chitale, Maitreya Prafulla
Shetye, Ketaki Mangesh
Gupta, Harshit
Chaudhary, Manav
Shrivastava, Manish
Varma, Vasudeva
author_facet Chitale, Maitreya Prafulla
Shetye, Ketaki Mangesh
Gupta, Harshit
Chaudhary, Manav
Shrivastava, Manish
Varma, Vasudeva
contents Obtaining high-quality, pre-submission feedback is a critical bottleneck in the academic publication lifecycle for researchers. We introduce AutoRev, an automated author-centric feedback system that generates structured, actionable guidance prior to formal peer review. AutoRev employs a graph-based retrieval-augmented generation framework that models each paper as a hierarchical document graph, integrating textual and structural representations to retrieve salient content efficiently. By leveraging graph-based passage retrieval, AutoRev substantially reduces LLM input context length, leading to higher-quality feedback generation. Experimental results demonstrate that AutoRev significantly outperforms baselines across multiple automatic evaluation metrics, while achieving strong performance in human evaluations. Code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-Guided Passage Retrieval for Author-Centric Structured Feedback
Chitale, Maitreya Prafulla
Shetye, Ketaki Mangesh
Gupta, Harshit
Chaudhary, Manav
Shrivastava, Manish
Varma, Vasudeva
Computation and Language
Obtaining high-quality, pre-submission feedback is a critical bottleneck in the academic publication lifecycle for researchers. We introduce AutoRev, an automated author-centric feedback system that generates structured, actionable guidance prior to formal peer review. AutoRev employs a graph-based retrieval-augmented generation framework that models each paper as a hierarchical document graph, integrating textual and structural representations to retrieve salient content efficiently. By leveraging graph-based passage retrieval, AutoRev substantially reduces LLM input context length, leading to higher-quality feedback generation. Experimental results demonstrate that AutoRev significantly outperforms baselines across multiple automatic evaluation metrics, while achieving strong performance in human evaluations. Code will be released upon acceptance.
title Graph-Guided Passage Retrieval for Author-Centric Structured Feedback
topic Computation and Language
url https://arxiv.org/abs/2505.14376