pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909509933334528 |
|---|---|
| author | Iyer, Kartheik G. Yunus, Mikaeel O'Neill, Charles Ye, Christine Hyk, Alina McCormick, Kiera Ciuca, Ioana Wu, John F. Accomazzi, Alberto Astarita, Simone Chakrabarty, Rishabh Cranney, Jesse Field, Anjalie Ghosal, Tirthankar Ginolfi, Michele Huertas-Company, Marc Jablonska, Maja Kruk, Sandor Liu, Huiling Marchidan, Gabriel Mistry, Rohit Naiman, J. P. Peek, J. E. G. Polimera, Mugdha Rodriguez, Sergio J. Schawinski, Kevin Sharma, Sanjib Smith, Michael J. Ting, Yuan-Sen Walmsley, Mike |
| author_facet | Iyer, Kartheik G. Yunus, Mikaeel O'Neill, Charles Ye, Christine Hyk, Alina McCormick, Kiera Ciuca, Ioana Wu, John F. Accomazzi, Alberto Astarita, Simone Chakrabarty, Rishabh Cranney, Jesse Field, Anjalie Ghosal, Tirthankar Ginolfi, Michele Huertas-Company, Marc Jablonska, Maja Kruk, Sandor Liu, Huiling Marchidan, Gabriel Mistry, Rohit Naiman, J. P. Peek, J. E. G. Polimera, Mugdha Rodriguez, Sergio J. Schawinski, Kevin Sharma, Sanjib Smith, Michael J. Ting, Yuan-Sen Walmsley, Mike |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01556 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy Iyer, Kartheik G. Yunus, Mikaeel O'Neill, Charles Ye, Christine Hyk, Alina McCormick, Kiera Ciuca, Ioana Wu, John F. Accomazzi, Alberto Astarita, Simone Chakrabarty, Rishabh Cranney, Jesse Field, Anjalie Ghosal, Tirthankar Ginolfi, Michele Huertas-Company, Marc Jablonska, Maja Kruk, Sandor Liu, Huiling Marchidan, Gabriel Mistry, Rohit Naiman, J. P. Peek, J. E. G. Polimera, Mugdha Rodriguez, Sergio J. Schawinski, Kevin Sharma, Sanjib Smith, Michael J. Ting, Yuan-Sen Walmsley, Mike Instrumentation and Methods for Astrophysics Digital Libraries Information Retrieval 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. |
| title | pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy |
| topic | Instrumentation and Methods for Astrophysics Digital Libraries Information Retrieval |
| url | https://arxiv.org/abs/2408.01556 |