PS-CoT-Adapter:adapting plan-and-solve chain-of-thought for ScienceQA  

作　　者：Qun LI Haixin SUN Fu XIAO Yiming WANG Xinping GAO Bir BHANU 

机构地区：[1]School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China [2]Purple Mountain Laboratories,Nanjing 211111,China [3]Department of Electrical and Computer Engineering,University of California at Riverside,Riverside 92521,USA

出　　处：《Science China(Information Sciences)》2025年第1期389-390,共2页中国科学(信息科学)(英文版)

基　　金：supported by National Natural Science Foundation of China(Grant Nos.62276143,62302233);Natural Science Foundation of Jiangsu Province(Grant No.BK20231287);National Science Fund for Distinguished Young Scholars of China(Grant No.62125203).

摘　　要：Large language models(LLMs)have recently shown remarkable performance in a variety of natural language processing(NLP)tasks.To further explore LLMs’reasoning abilities in solving complex problems,recent research[1–3]has investigated chain-of-thought(CoT)reasoning in complex multimodal scenarios,such as science question answering(ScienceQA)tasks[4],by fine-tuning multimodal models through human-annotated CoT rationales.However,collected CoT rationales often miss the necessary reasoning steps and specific expertise.

关 键 词：reasoning rational modal 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]