Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Xufeng, Li, Mengdi, Lu, Wenhao, Weber, Cornelius, Lee, Jae Hee, Chu, Kun, Wermter, Stefan
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929288327987200
author Zhao, Xufeng
Li, Mengdi
Lu, Wenhao
Weber, Cornelius
Lee, Jae Hee
Chu, Kun
Wermter, Stefan
author_facet Zhao, Xufeng
Li, Mengdi
Lu, Wenhao
Weber, Cornelius
Lee, Jae Hee
Chu, Kun
Wermter, Stefan
contents Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios requiring multi-step reasoning. Although large language models possess extensive knowledge, their reasoning often fails to effectively utilize this knowledge to establish a coherent thinking paradigm. These models sometimes show hallucinations as their reasoning procedures are unconstrained by logical principles. Aiming at improving the zero-shot chain-of-thought reasoning ability of large language models, we propose LoT (Logical Thoughts), a self-improvement prompting framework that leverages principles rooted in symbolic logic, particularly Reductio ad Absurdum, to systematically verify and rectify the reasoning processes step by step. Experimental evaluations conducted on language tasks in diverse domains, including arithmetic, commonsense, symbolic, causal inference, and social problems, demonstrate the efficacy of enhanced reasoning by logic. The implementation code for LoT can be accessed at: https://github.com/xf-zhao/LoT.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13339
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic
Zhao, Xufeng
Li, Mengdi
Lu, Wenhao
Weber, Cornelius
Lee, Jae Hee
Chu, Kun
Wermter, Stefan
Computation and Language
Artificial Intelligence
Machine Learning
Symbolic Computation
Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios requiring multi-step reasoning. Although large language models possess extensive knowledge, their reasoning often fails to effectively utilize this knowledge to establish a coherent thinking paradigm. These models sometimes show hallucinations as their reasoning procedures are unconstrained by logical principles. Aiming at improving the zero-shot chain-of-thought reasoning ability of large language models, we propose LoT (Logical Thoughts), a self-improvement prompting framework that leverages principles rooted in symbolic logic, particularly Reductio ad Absurdum, to systematically verify and rectify the reasoning processes step by step. Experimental evaluations conducted on language tasks in diverse domains, including arithmetic, commonsense, symbolic, causal inference, and social problems, demonstrate the efficacy of enhanced reasoning by logic. The implementation code for LoT can be accessed at: https://github.com/xf-zhao/LoT.
title Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic
topic Computation and Language
Artificial Intelligence
Machine Learning
Symbolic Computation
url https://arxiv.org/abs/2309.13339