LogiCoT: Logical Chain-of-Thought Instruction-Tuning

Hanmeng Liu, Zhiyang Teng, Leyang Cui, Chaoli Zhang, Qiji Zhou +1 more
5/20/2023
cs.CLcs.AI

No official code found. Best implementation: csitfun/LogiCoT (54 stars, last commit 2024-09-03).

Abstract

Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models. These instructions enable the model to achieve performance comparable to GPT-3.5 on general tasks like open-domain text generation and paraphrasing. However, they fall short of helping the model handle complex reasoning tasks. To bridge the gap, this paper presents LogiCoT, a new instruction-tuning dataset for Logical Chain-of-Thought reasoning with GPT-4. We elaborate on the process of harvesting instructions for prompting GPT-4 to generate chain-of-thought rationales. LogiCoT serves as an instruction set for teaching models of logical reasoning and elicits general reasoning skills.

View on arXivView PDF

Code Implementations(1)

csitfun/LogiCoTCommunity100%

the instructions and demonstrations for building a formal logical reasoning capable GLM

543Apr 24, 20232 years ago

Similar Papers

Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models

85% match1 repo862023

Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step

85% match1 repo162023

Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models

85% match2026

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

84% match1 repo432023

Certified Deductive Reasoning with Language Models

84% match2023

Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data

84% match2 repos202023

Cite this paper

@article{liu2023logicot,
  title  = {LogiCoT: Logical Chain-of-Thought Instruction-Tuning},
  author = {Hanmeng Liu and Zhiyang Teng and Leyang Cui and Chaoli Zhang and Qiji Zhou and Yue Zhang},
  year   = {2023},
  eprint = {2305.12147},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.12147v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.12147.svg)](https://codeofpaper.com/paper/2305.12147)

Discussion