Abductive Reasoning with Syllogistic Forms in Large Language Models

2026-03-06

HAR

AI Summary

This study investigates whether large language models exhibit human-like cognitive biases in abductive reasoning, focusing on non-deductive inference tasks framed within syllogistic structures. To this end, the authors systematically reformulate traditional syllogisms into an abductive format—inferring the minor premise given the conclusion and major premise—and introduce a novel benchmark that integrates contextualized reasoning to evaluate both accuracy and plausibility. Experimental results reveal that current models remain susceptible to commonsense belief interference, leading to biased inferences and highlighting their limitations in complex abductive reasoning. This work not only presents an innovative framework for modeling and evaluating abductive reasoning in language models but also identifies key directions for advancing their human-like reasoning capabilities.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key concern. Prior studies have indicated that LLMs and humans share similar biases, such as dismissing logically valid inferences that contradict common beliefs. However, criticizing LLMs for these biases might be unfair, considering our reasoning not only involves formal deduction but also abduction, which draws tentative conclusions from limited information. Abduction can be regarded as the inverse form of syllogism in its basic structure, that is, a process of drawing a minor premise from a major premise and conclusion. This paper explores the accuracy of LLMs in abductive reasoning by converting a syllogistic dataset into one suitable for abduction. It aims to investigate whether the state-of-the-art LLMs exhibit biases in abduction and to identify potential areas for improvement, emphasizing the importance of contextualized reasoning beyond formal deduction. This investigation is vital for advancing the understanding and application of LLMs in complex reasoning tasks, offering insights into bridging the gap between machine and human cognition.

Problem

• abductive reasoning
• syllogism
• large language models
• reasoning bias
• contextualized reasoning

Innovation

• abductive reasoning
• syllogistic forms
• large language models
• reasoning bias
• contextualized reasoning