CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning
It addresses the problem of determining cause authenticity in abductive reasoning for AI systems, representing a novel method for a known bottleneck.
The paper tackles abductive logical reasoning in LLMs by proposing CauseJudger, a framework that transforms thinking from reverse to forward and removes irrelevant information, achieving a maximum correctness improvement of 41% with GPT-3.5 and over 90% accuracy with GPT-4.
Large language models (LLMs) have been utilized in solving diverse reasoning tasks, encompassing common sense, arithmetic and deduction tasks. However, with difficulties of reversing thinking patterns and irrelevant premises, how to determine the authenticity of the cause in abductive logical reasoning remains underexplored. Inspired by hypothesis and verification method and identification of irrelevant information in human thinking process, we propose a new framework for LLMs abductive logical reasoning called CauseJudger (CJ), which identifies the authenticity of possible cause by transforming thinking from reverse to forward and removing irrelevant information. In addition, we construct an abductive logical reasoning dataset for decision task called CauseLogics, which contains 200,000 tasks of varying reasoning lengths. Our experiments show the efficiency of CJ with overall experiments and ablation experiments as well as case studies on our dataset and reconstructed public dataset. Notably, CJ's implementation is efficient, requiring only two calls to LLM. Its impact is profound: when using gpt-3.5, CJ achieves a maximum correctness improvement of 41% compared to Zero-Shot-CoT. Moreover, with gpt-4, CJ attains an accuracy exceeding 90% across all datasets.