Salvato in:
Dettagli Bibliografici
Autori principali: Zaoad, Md Shahir, Zawad, Niamat, Ranade, Priyanka, Krogman, Richard, Khan, Latifur, Holt, James
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.14802
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910883300507648
author Zaoad, Md Shahir
Zawad, Niamat
Ranade, Priyanka
Krogman, Richard
Khan, Latifur
Holt, James
author_facet Zaoad, Md Shahir
Zawad, Niamat
Ranade, Priyanka
Krogman, Richard
Khan, Latifur
Holt, James
contents Knowledge graphs have emerged to be promising datastore candidates for context augmentation during Retrieval Augmented Generation (RAG). As a result, techniques in graph representation learning have been simultaneously explored alongside principal neural information retrieval approaches, such as two-phased retrieval, also known as re-ranking. While Graph Neural Networks (GNNs) have been proposed to demonstrate proficiency in graph learning for re-ranking, there are ongoing limitations in modeling and evaluating input graph structures for training and evaluation for passage and document ranking tasks. In this survey, we review emerging GNN-based ranking model architectures along with their corresponding graph representation construction methodologies. We conclude by providing recommendations on future research based on community-wide challenges and opportunities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14802
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities
Zaoad, Md Shahir
Zawad, Niamat
Ranade, Priyanka
Krogman, Richard
Khan, Latifur
Holt, James
Information Retrieval
N/A
Knowledge graphs have emerged to be promising datastore candidates for context augmentation during Retrieval Augmented Generation (RAG). As a result, techniques in graph representation learning have been simultaneously explored alongside principal neural information retrieval approaches, such as two-phased retrieval, also known as re-ranking. While Graph Neural Networks (GNNs) have been proposed to demonstrate proficiency in graph learning for re-ranking, there are ongoing limitations in modeling and evaluating input graph structures for training and evaluation for passage and document ranking tasks. In this survey, we review emerging GNN-based ranking model architectures along with their corresponding graph representation construction methodologies. We conclude by providing recommendations on future research based on community-wide challenges and opportunities.
title Graph-Based Re-ranking: Emerging Techniques, Limitations, and Opportunities
topic Information Retrieval
N/A
url https://arxiv.org/abs/2503.14802