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

ACL ARR 2026 January Submission5957 Authors

Keywords: Mechanistic Interpretability, Large Language Models, Propositional Logic Reasoning, Activation Patching, Attention Heads, Implict Reasoning

Abstract:

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying task-specific 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.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: probing, knowledge tracing/discovering/inducing, feature attribution

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 5957