pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy

Abstract

The exponential growth of astronomical literature poses significant challenges for researchers navigating and synthesizing general insights or even domain-specific knowledge. We present Pathfinder, a machine learning framework designed to enable literature review and knowledge discovery in astronomy, focusing on semantic searching with natural language instead of syntactic searches with keywords. Utilizing state-of-the-art large language models (LLMs) and a corpus of 350,000 peer-reviewed papers from the Astrophysics Data System (ADS), Pathfinder offers an innovative approach to scientific inquiry and literature exploration. Our framework couples advanced retrieval techniques with LLM-based synthesis to search astronomical literature by semantic context as a complement to currently existing methods that use keywords or citation graphs. It addresses complexities of jargon, named entities, and temporal aspects through time-based and citation-based weighting schemes. We demonstrate the tool's versatility through case studies, showcasing its application in various research scenarios. The system's performance is evaluated using custom benchmarks, including single-paper and multi-paper tasks. Beyond literature review, Pathfinder offers unique capabilities for reformatting answers in ways that are accessible to various audiences (e.g. in a different language or as simplified text), visualizing research landscapes, and tracking the impact of observatories and methodologies. This tool represents a significant advancement in applying AI to astronomical research, aiding researchers at all career stages in navigating modern astronomy literature.

25 pages, 9 figures, submitted to AAS jorunals. Comments are welcome, and the tools mentioned are available online at https://pfdr.app

References in corpus (7)

• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• The NASA Astrophysics Data System: Architecture
• Canvas and Cosmos: Visual Art Techniques Applied to Astronomy Data
• The Unified Astronomy Thesaurus: Semantic Metadata for Astronomy and Astrophysics
• How cost impacts equitable participation in astronomy outreach events

Cited by in corpus (4)

• Insights from leptohadronic modelling of the brightest blazar flare
• Feeding the Dead: Neutral Gas Inflow in a Long-Quenched Ancient Massive Galaxy at $z\sim 2.7$ Observed with JWST/NIRSpec
• Betelgeuse's Buddy: X-Ray Constraints on the Nature of $\alpha$ Ori B
• The Exoplanet Edge: Planets Don't Induce Observable TTVs with a Dominant TTV Period Faster than Half their Orbital Period