Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2601.04260v1
• Date: Wed, 07 Jan 2026 04:20:30 GMT
• Title: Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
• Authors: Danchun Chen, Qiyao Yan, Liangming Pan,
• Abstract summary: Analysis of Qwen3 (8B and 14B) on PropLogic-MI, a dataset spanning 11 propositional logic rule categories across one-hop and two-hop reasoning.<n>Our analysis reveals a coherent computational architecture comprising four interlocking mechanisms.<n>These mechanisms generalize across model scales, rule types, and reasoning depths, providing mechanistic evidence that LLMs employ structured computational strategies for logical reasoning.
• Score: 31.709549159768727
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what computational strategies LLMs employ for propositional reasoning. We address this gap through comprehensive analysis of Qwen3 (8B and 14B) on PropLogic-MI, a controlled dataset spanning 11 propositional logic rule categories across one-hop and two-hop reasoning. Rather than asking ''which components are necessary,'' we ask ''how does the model organize computation?'' Our analysis reveals a coherent computational architecture comprising four interlocking mechanisms: Staged Computation (layer-wise processing phases), Information Transmission (information flow aggregation at boundary tokens), Fact Retrospection (persistent re-access of source facts), and Specialized Attention Heads (functionally distinct head types). These mechanisms generalize across model scales, rule types, and reasoning depths, providing mechanistic evidence that LLMs employ structured computational strategies for logical reasoning.

Related papers

• Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning [55.55968342644846]
  Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text.<n>We propose the textitLogits-to-Logic framework, which incorporates logits strengthening and logits filtering as core modules to correct logical defects in LLM outputs.
  arXiv  Detail & Related papers  (2025-11-11T07:08:27Z)
• Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning [8.248971739035746]
  Large Language Models (LLMs) display striking surface fluency yet systematically fail at tasks requiring symbolic reasoning, arithmetic accuracy, and logical consistency.<n>This paper offers a structural diagnosis of such failures, revealing a persistent gap between textitcomprehension and textitcompetence<n>We term this phenomenon the computational textitsplit-brain syndrome, where instruction and action pathways are geometrically and functionally dissociated.
  arXiv  Detail & Related papers  (2025-07-14T04:01:45Z)
• KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation [35.555200530999365]
  We introduce KAG-Thinker, which upgrade KAG to a multi-turn interactive thinking and deep reasoning framework powered by a dedicated parameter-light large language model (LLM)<n>Our approach constructs a structured thinking process for solving complex problems, enhancing the the logical coherence and contextual consistency of the reasoning process.
  arXiv  Detail & Related papers  (2025-06-21T14:58:53Z)
• LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning [74.0242521818214]
  This paper systematically investigates the comparative dynamics of inductive (System 1) versus abductive/deductive (System 2) inference in large language models (LLMs)<n>We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text)<n>Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems.
  arXiv  Detail & Related papers  (2025-02-16T15:54:53Z)
• Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism [68.05754701230039]
  We construct a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models.<n>We propose a random matrix-based algorithm to enhance the model's reasoning ability.
  arXiv  Detail & Related papers  (2024-05-24T07:41:26Z)
• Logic Agent: Enhancing Validity with Logic Rule Invocation [24.815341366820753]
  Chain-of-Thought prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks.<n>This paper introduces the Logic Agent (LA), an agent-based framework aimed at enhancing the validity of reasoning processes in Large Language Models.
  arXiv  Detail & Related papers  (2024-04-28T10:02:28Z)
• LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models [63.14196038655506]
  We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) Our methodology reveals significant gaps in LLMs' learning of logical rules, with identified reasoning failures ranging from 29% to 90% across different models. We leverage these findings to construct targeted demonstration examples and fine-tune data, notably enhancing logical reasoning in models like GPT-4o by up to 5%.
  arXiv  Detail & Related papers  (2024-01-01T13:53:53Z)
• Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
  Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning. We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
  arXiv  Detail & Related papers  (2023-10-02T01:00:50Z)
• Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension [80.99865844249106]
  We propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism.
  arXiv  Detail & Related papers  (2023-06-21T07:34:27Z)
• Exploring Self-supervised Logic-enhanced Training for Large Language Models [59.227222647741094]
  In this paper, we make the first attempt to investigate the feasibility of incorporating logical knowledge through self-supervised post-training. We devise an auto-regressive objective variant of MERIt and integrate it with two LLM series, i.e., FLAN-T5 and LLaMA, with parameter size ranging from 3 billion to 13 billion. The results on two challenging logical reasoning benchmarks demonstrate the effectiveness of LogicLLM.
  arXiv  Detail & Related papers  (2023-05-23T06:13:10Z)
• Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs [67.043747188954]
  We propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs. It encodes linearized query structures and entities using pre-trained language models to find answers. We conduct experiments on two inductive logical reasoning datasets and three transductive datasets.
  arXiv  Detail & Related papers  (2023-05-23T01:25:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.