Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pang, Xinyu, Hong, Ruixin, Zhou, Zhanke, Lv, Fangrui, Yang, Xinwei, Liang, Zhilong, Han, Bo, Zhang, Changshui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917872396140544
author Pang, Xinyu
Hong, Ruixin
Zhou, Zhanke
Lv, Fangrui
Yang, Xinwei
Liang, Zhilong
Han, Bo
Zhang, Changshui
author_facet Pang, Xinyu
Hong, Ruixin
Zhou, Zhanke
Lv, Fangrui
Yang, Xinwei
Liang, Zhilong
Han, Bo
Zhang, Changshui
contents Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. To mitigate these issues, we propose Physics Reasoner, a knowledge-augmented framework to solve physics problems with LLMs. Specifically, the proposed framework constructs a comprehensive formula set to provide explicit physics knowledge and utilizes checklists containing detailed instructions to guide effective knowledge application. Namely, given a physics problem, Physics Reasoner solves it through three stages: problem analysis, formula retrieval, and guided reasoning. During the process, checklists are employed to enhance LLMs' self-improvement in the analysis and reasoning stages. Empirically, Physics Reasoner mitigates the issues of insufficient knowledge and incorrect application, achieving state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13791
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
Pang, Xinyu
Hong, Ruixin
Zhou, Zhanke
Lv, Fangrui
Yang, Xinwei
Liang, Zhilong
Han, Bo
Zhang, Changshui
Computation and Language
Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. To mitigate these issues, we propose Physics Reasoner, a knowledge-augmented framework to solve physics problems with LLMs. Specifically, the proposed framework constructs a comprehensive formula set to provide explicit physics knowledge and utilizes checklists containing detailed instructions to guide effective knowledge application. Namely, given a physics problem, Physics Reasoner solves it through three stages: problem analysis, formula retrieval, and guided reasoning. During the process, checklists are employed to enhance LLMs' self-improvement in the analysis and reasoning stages. Empirically, Physics Reasoner mitigates the issues of insufficient knowledge and incorrect application, achieving state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.
title Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2412.13791