Saved in:
Bibliographic Details
Main Authors: Ghanadian, Hamideh, Kamali, Amin, Tekieh, Mohammad Hossein
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.17856
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917283815751680
author Ghanadian, Hamideh
Kamali, Amin
Tekieh, Mohammad Hossein
author_facet Ghanadian, Hamideh
Kamali, Amin
Tekieh, Mohammad Hossein
contents This paper investigates the enhancement of scientific literature chatbots through retrieval-augmented generation (RAG), with a focus on evaluating vector- and graph-based retrieval systems. The proposed chatbot leverages both structured (graph) and unstructured (vector) databases to access scientific articles and gray literature, enabling efficient triage of sources according to research objectives. To systematically assess performance, we examine two use-case scenarios: retrieval from a single uploaded document and retrieval from a large-scale corpus. Benchmark test sets were generated using a GPT model, with selected outputs annotated for evaluation. The comparative analysis emphasizes retrieval accuracy and response relevance, providing insight into the strengths and limitations of each approach. The findings demonstrate the potential of hybrid RAG systems to improve accessibility to scientific knowledge and to support evidence-based decision making.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems
Ghanadian, Hamideh
Kamali, Amin
Tekieh, Mohammad Hossein
Information Retrieval
Artificial Intelligence
I.2.7; H.3.1
This paper investigates the enhancement of scientific literature chatbots through retrieval-augmented generation (RAG), with a focus on evaluating vector- and graph-based retrieval systems. The proposed chatbot leverages both structured (graph) and unstructured (vector) databases to access scientific articles and gray literature, enabling efficient triage of sources according to research objectives. To systematically assess performance, we examine two use-case scenarios: retrieval from a single uploaded document and retrieval from a large-scale corpus. Benchmark test sets were generated using a GPT model, with selected outputs annotated for evaluation. The comparative analysis emphasizes retrieval accuracy and response relevance, providing insight into the strengths and limitations of each approach. The findings demonstrate the potential of hybrid RAG systems to improve accessibility to scientific knowledge and to support evidence-based decision making.
title Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems
topic Information Retrieval
Artificial Intelligence
I.2.7; H.3.1
url https://arxiv.org/abs/2602.17856