{"title":"Multimessenger天文学的语言模型","authors":"Vladimir Sotnikov, Anastasiia Chaikova","doi":"10.3390/galaxies11030063","DOIUrl":null,"url":null,"abstract":"With the increasing reliance of astronomy on multi-instrument and multi-messenger observations for detecting transient phenomena, communication among astronomers has become more critical. Apart from automatic prompt follow-up observations, short reports, e.g., GCN circulars and ATels, provide essential human-written interpretations and discussions of observations. These reports lack a defined format, unlike machine-readable messages, making it challenging to associate phenomena with specific objects or coordinates in the sky. This paper examines the use of large language models (LLMs)—machine learning models with billions of trainable parameters or more that are trained on text—such as InstructGPT-3 and open-source Flan-T5-XXL for extracting information from astronomical reports. The study investigates the zero-shot and few-shot learning capabilities of LLMs and demonstrates various techniques to improve the accuracy of predictions. The study shows the importance of careful prompt engineering while working with LLMs, as demonstrated through edge case examples. The study’s findings have significant implications for the development of data-driven applications for astrophysical text analysis.","PeriodicalId":37570,"journal":{"name":"Galaxies","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Language Models for Multimessenger Astronomy\",\"authors\":\"Vladimir Sotnikov, Anastasiia Chaikova\",\"doi\":\"10.3390/galaxies11030063\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the increasing reliance of astronomy on multi-instrument and multi-messenger observations for detecting transient phenomena, communication among astronomers has become more critical. Apart from automatic prompt follow-up observations, short reports, e.g., GCN circulars and ATels, provide essential human-written interpretations and discussions of observations. These reports lack a defined format, unlike machine-readable messages, making it challenging to associate phenomena with specific objects or coordinates in the sky. This paper examines the use of large language models (LLMs)—machine learning models with billions of trainable parameters or more that are trained on text—such as InstructGPT-3 and open-source Flan-T5-XXL for extracting information from astronomical reports. The study investigates the zero-shot and few-shot learning capabilities of LLMs and demonstrates various techniques to improve the accuracy of predictions. The study shows the importance of careful prompt engineering while working with LLMs, as demonstrated through edge case examples. The study’s findings have significant implications for the development of data-driven applications for astrophysical text analysis.\",\"PeriodicalId\":37570,\"journal\":{\"name\":\"Galaxies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Galaxies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/galaxies11030063\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ASTRONOMY & ASTROPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Galaxies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/galaxies11030063","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
With the increasing reliance of astronomy on multi-instrument and multi-messenger observations for detecting transient phenomena, communication among astronomers has become more critical. Apart from automatic prompt follow-up observations, short reports, e.g., GCN circulars and ATels, provide essential human-written interpretations and discussions of observations. These reports lack a defined format, unlike machine-readable messages, making it challenging to associate phenomena with specific objects or coordinates in the sky. This paper examines the use of large language models (LLMs)—machine learning models with billions of trainable parameters or more that are trained on text—such as InstructGPT-3 and open-source Flan-T5-XXL for extracting information from astronomical reports. The study investigates the zero-shot and few-shot learning capabilities of LLMs and demonstrates various techniques to improve the accuracy of predictions. The study shows the importance of careful prompt engineering while working with LLMs, as demonstrated through edge case examples. The study’s findings have significant implications for the development of data-driven applications for astrophysical text analysis.
GalaxiesPhysics and Astronomy-Astronomy and Astrophysics
CiteScore
4.90
自引率
12.00%
发文量
100
审稿时长
11 weeks
期刊介绍:
Es una revista internacional de acceso abierto revisada por pares que proporciona un foro avanzado para estudios relacionados con astronomía, astrofísica y cosmología. Areas temáticas Astronomía Astrofísica Cosmología Astronomía observacional: radio, infrarrojo, óptico, rayos X, neutrino, etc. Ciencia planetaria Equipos y tecnologías de astronomía. Ingeniería Aeroespacial Análisis de datos astronómicos. Astroquímica y Astrobiología. Arqueoastronomía Historia de la astronomía y cosmología. Problemas filosóficos en cosmología.