SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

2025-01-20

AI Summary

Large language models (LLMs) often deviate from logical reasoning paths and exhibit insufficient accuracy in knowledge-driven deductive reasoning, especially under chain-of-thought prompting. To address this, we propose SR-FoT—a multi-stage syllogistic reasoning framework grounded in formal logic. SR-FoT explicitly models a closed-loop three-phase process: major premise generation, minor premise matching, and conclusion derivation. It integrates semantic parsing, stepwise prompt engineering, and premise-guided generation to construct structured, interpretable reasoning chains—without fine-tuning or external knowledge bases. Evaluated on multiple knowledge-intensive reasoning benchmarks, SR-FoT significantly outperforms state-of-the-art methods including Chain-of-Thought and Self-Consistency. It achieves comprehensive improvements in reasoning accuracy, process interpretability, and robustness to input perturbations. To our knowledge, SR-FoT is the first framework to systematically embed the human syllogistic reasoning paradigm into LLM inference workflows.

Technology Category

• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Deductive reasoning is a crucial logical capability that assists us in solving complex problems based on existing knowledge. Although augmented by Chain-of-Thought prompts, Large Language Models (LLMs) might not follow the correct reasoning paths. Enhancing the deductive reasoning abilities of LLMs, and leveraging their extensive built-in knowledge for various reasoning tasks, remains an open question. Attempting to mimic the human deductive reasoning paradigm, we propose a multi-stage Syllogistic-Reasoning Framework of Thought (SR-FoT) that enables LLMs to perform syllogistic deductive reasoning to handle complex knowledge-based reasoning tasks. Our SR-FoT begins by interpreting the question and then uses the interpretation and the original question to propose a suitable major premise. It proceeds by generating and answering minor premise questions in two stages to match the minor premises. Finally, it guides LLMs to use the previously generated major and minor premises to perform syllogistic deductive reasoning to derive the answer to the original question. Extensive and thorough experiments on knowledge-based reasoning tasks have demonstrated the effectiveness and advantages of our SR-FoT.

Problem

• Large Language Models
• Knowledge Reasoning
• Deductive Inference

Innovation

• SR-FoT
• Knowledge Reasoning
• Large Language Model (LLM)