DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought structures like chains, trees, or graphs. However, LLM-based reasoning still encounters the following challenges: (1) Limited adaptability of preset structures to diverse tasks; (2) Insufficient precision in exploiting known conditions to derive new ones; and (3) Inadequate consideration of historical reasoning experiences for subsequent reasoning steps. To this end, we propose DetermLR, a novel perspective that rethinks the reasoning process as an evolution from indeterminacy to determinacy. First, we categorize known conditions into two types: determinate and indeterminate premises, facilitating the transformation process. Subsequently, we leverage quantitative measurements to prioritize more relevant premises to explore new insights. Furthermore, we automate the storage and extraction of available premises and reasoning paths with reasoning memory, preserving historical reasoning details for future use. Comprehensive experimental results demonstrate that DetermLR surpasses all baselines on logical reasoning benchmarks: LogiQA, ProofWriter, FOLIO, PrOn-toQA, and LogicalDeduction. Compared to previous multi-step reasoning methods, DetermLR achieves higher accuracy with fewer reasoning steps, highlighting its superior efficiency and effectiveness in solving logical reasoning tasks. ment of research and applications of cognitive in-044 telligence (Huang and Chang, 2022). However, 045 even the current state-of-the-art (SOTA) LLMs still 046 grapple with a key limitation: the lack of human-047 like advanced reasoning skills to rationally analyze 048 known conditions and draw conclusions (Arkoudas, 049 2023; Singh et al., 2023). This leaves a substantial 050 gap between LLM-based reasoning and the cogni-051 tive process of human reasoning.