AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zhifeng, Li, Jason Jingshi, Zhang, Kaihao, Sankaranarayana, Ramesh
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913160042119168
author Wang, Zhifeng
Li, Jason Jingshi
Zhang, Kaihao
Sankaranarayana, Ramesh
author_facet Wang, Zhifeng
Li, Jason Jingshi
Zhang, Kaihao
Sankaranarayana, Ramesh
contents Large language models (LLMs) demonstrate strong performance in natural language processing but often generate factual errors when relying solely on parametric knowledge. Retrieval-Augmented Generation (RAG) mitigates these errors by grounding responses in external evidence, yet conventional retrieve-and-dump approaches frequently introduce irrelevant context that degrades answer quality. In this work, we present AstroRAG -- a PageRank-based retrieval-augmented generation (RAG) pipeline adapted for question answering in astronomy. The system performs token-aware chunking and per-instance, ephemeral indexing in Elasticsearch, then executes a two-stage retrieval: (i) Maximal Marginal Relevance (MMR) to obtain a small, diverse candidate set and (ii) a reader-driven PageRank (PR) re-ranking on a similarity graph to identify a compact, mutually supportive context under a strict token budget. Our design is training-free, privacy-preserving, and reproducible, as each instance is processed through transient indexing to prevent cross-task leakage. We evaluate the pipeline on the AstroQA benchmark for astronomy QA, and demonstrate competitive performance across all difficulty levels. In particular, the RAG-enhanced Mistral-7B achieves \textbf{79.49\% accuracy} and \textbf{79.49\% F1-score}, nearly doubling the performance of its non-RAG counterpart. These results highlight the effectiveness of disciplined retrieval and refinement in boosting domain-specific reasoning, establishing a robust foundation for extending RAG to other scientific fields.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25039
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy
Wang, Zhifeng
Li, Jason Jingshi
Zhang, Kaihao
Sankaranarayana, Ramesh
Computer Vision and Pattern Recognition
Large language models (LLMs) demonstrate strong performance in natural language processing but often generate factual errors when relying solely on parametric knowledge. Retrieval-Augmented Generation (RAG) mitigates these errors by grounding responses in external evidence, yet conventional retrieve-and-dump approaches frequently introduce irrelevant context that degrades answer quality. In this work, we present AstroRAG -- a PageRank-based retrieval-augmented generation (RAG) pipeline adapted for question answering in astronomy. The system performs token-aware chunking and per-instance, ephemeral indexing in Elasticsearch, then executes a two-stage retrieval: (i) Maximal Marginal Relevance (MMR) to obtain a small, diverse candidate set and (ii) a reader-driven PageRank (PR) re-ranking on a similarity graph to identify a compact, mutually supportive context under a strict token budget. Our design is training-free, privacy-preserving, and reproducible, as each instance is processed through transient indexing to prevent cross-task leakage. We evaluate the pipeline on the AstroQA benchmark for astronomy QA, and demonstrate competitive performance across all difficulty levels. In particular, the RAG-enhanced Mistral-7B achieves \textbf{79.49\% accuracy} and \textbf{79.49\% F1-score}, nearly doubling the performance of its non-RAG counterpart. These results highlight the effectiveness of disciplined retrieval and refinement in boosting domain-specific reasoning, establishing a robust foundation for extending RAG to other scientific fields.
title AstroRAG -- A Pagerank-Based Retrieval-Augmented Generation Pipeline for Question Answering in Astronomy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.25039