{"title":"大型语言模型能否开启科研新思路?","authors":"Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif Ekbal","doi":"arxiv-2409.06185","DOIUrl":null,"url":null,"abstract":"\"An idea is nothing more nor less than a new combination of old elements\"\n(Young, J.W.). The widespread adoption of Large Language Models (LLMs) and\npublicly available ChatGPT have marked a significant turning point in the\nintegration of Artificial Intelligence (AI) into people's everyday lives. This\nstudy explores the capability of LLMs in generating novel research ideas based\non information from research papers. We conduct a thorough examination of 4\nLLMs in five domains (e.g., Chemistry, Computer, Economics, Medical, and\nPhysics). We found that the future research ideas generated by Claude-2 and\nGPT-4 are more aligned with the author's perspective than GPT-3.5 and Gemini.\nWe also found that Claude-2 generates more diverse future research ideas than\nGPT-4, GPT-3.5, and Gemini 1.0. We further performed a human evaluation of the\nnovelty, relevancy, and feasibility of the generated future research ideas.\nThis investigation offers insights into the evolving role of LLMs in idea\ngeneration, highlighting both its capability and limitations. Our work\ncontributes to the ongoing efforts in evaluating and utilizing language models\nfor generating future research ideas. We make our datasets and codes publicly\navailable.","PeriodicalId":501541,"journal":{"name":"arXiv - CS - Human-Computer Interaction","volume":"10 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Can Large Language Models Unlock Novel Scientific Research Ideas?\",\"authors\":\"Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, Asif Ekbal\",\"doi\":\"arxiv-2409.06185\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\\"An idea is nothing more nor less than a new combination of old elements\\\"\\n(Young, J.W.). The widespread adoption of Large Language Models (LLMs) and\\npublicly available ChatGPT have marked a significant turning point in the\\nintegration of Artificial Intelligence (AI) into people's everyday lives. This\\nstudy explores the capability of LLMs in generating novel research ideas based\\non information from research papers. We conduct a thorough examination of 4\\nLLMs in five domains (e.g., Chemistry, Computer, Economics, Medical, and\\nPhysics). We found that the future research ideas generated by Claude-2 and\\nGPT-4 are more aligned with the author's perspective than GPT-3.5 and Gemini.\\nWe also found that Claude-2 generates more diverse future research ideas than\\nGPT-4, GPT-3.5, and Gemini 1.0. We further performed a human evaluation of the\\nnovelty, relevancy, and feasibility of the generated future research ideas.\\nThis investigation offers insights into the evolving role of LLMs in idea\\ngeneration, highlighting both its capability and limitations. Our work\\ncontributes to the ongoing efforts in evaluating and utilizing language models\\nfor generating future research ideas. We make our datasets and codes publicly\\navailable.\",\"PeriodicalId\":501541,\"journal\":{\"name\":\"arXiv - CS - Human-Computer Interaction\",\"volume\":\"10 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Human-Computer Interaction\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06185\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Human-Computer Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06185","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Can Large Language Models Unlock Novel Scientific Research Ideas?
"An idea is nothing more nor less than a new combination of old elements"
(Young, J.W.). The widespread adoption of Large Language Models (LLMs) and
publicly available ChatGPT have marked a significant turning point in the
integration of Artificial Intelligence (AI) into people's everyday lives. This
study explores the capability of LLMs in generating novel research ideas based
on information from research papers. We conduct a thorough examination of 4
LLMs in five domains (e.g., Chemistry, Computer, Economics, Medical, and
Physics). We found that the future research ideas generated by Claude-2 and
GPT-4 are more aligned with the author's perspective than GPT-3.5 and Gemini.
We also found that Claude-2 generates more diverse future research ideas than
GPT-4, GPT-3.5, and Gemini 1.0. We further performed a human evaluation of the
novelty, relevancy, and feasibility of the generated future research ideas.
This investigation offers insights into the evolving role of LLMs in idea
generation, highlighting both its capability and limitations. Our work
contributes to the ongoing efforts in evaluating and utilizing language models
for generating future research ideas. We make our datasets and codes publicly
available.