# Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems

arXiv: https://arxiv.org/abs/2602.17856 · HTML: https://mlsanity.com/paper/2602.17856/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 9 of 9)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Evaluating Retrieval Quality in Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.13781/) (2024)
- [PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths](https://mlsanity.com/paper/2502.14902/) (2025)
- [Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models](https://mlsanity.com/paper/2402.01712/) (2024)
- [A review of faithfulness metrics for hallucination assessment in Large Language Models](https://mlsanity.com/paper/2501.00269/) (2024)
- [TrustRAG: An Information Assistant with Retrieval Augmented Generation](https://mlsanity.com/paper/2502.13719/) (2025)

## Abstract (arXiv)

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.