Toward Mechanistic Explanation of Deductive Reasoning in Language Models

• URL: http://arxiv.org/abs/2510.09340v1
• Date: Fri, 10 Oct 2025 12:49:00 GMT
• Title: Toward Mechanistic Explanation of Deductive Reasoning in Language Models
• Authors: Davide Maltoni, Matteo Ferrara,
• Abstract summary: We show that a small language model can solve a deductive reasoning task by learning the underlying rules.<n>Our findings reveal that induction heads play a central role in the implementation of the rule completion and rule chaining steps.
• Score: 2.196417293457801
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent large language models have demonstrated relevant capabilities in solving problems that require logical reasoning; however, the corresponding internal mechanisms remain largely unexplored. In this paper, we show that a small language model can solve a deductive reasoning task by learning the underlying rules (rather than operating as a statistical learner). A low-level explanation of its internal representations and computational circuits is then provided. Our findings reveal that induction heads play a central role in the implementation of the rule completion and rule chaining steps involved in the logical inference required by the task.

Related papers

• Are Language Models Efficient Reasoners? A Perspective from Logic Programming [109.47572890883248]
  Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of human-like reasoning: efficiency.<n>We propose a framework for assessing LM reasoning efficiency through the lens of logic programming.
  arXiv  Detail & Related papers  (2025-10-29T15:30:31Z)
• A Survey of Inductive Reasoning for Large Language Models [55.23215679173251]
  The inductive mode is crucial for knowledge generalization and aligns better with human cognition.<n>Despite the importance of inductive reasoning, there is no systematic summary of it.<n>This paper presents the first comprehensive survey of inductive reasoning for large language models.
  arXiv  Detail & Related papers  (2025-10-11T11:45:38Z)
• 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)
• Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning [9.795934690403374]
  It is still unclear which multi-step reasoning mechanisms are used by language models to solve such tasks.<n>We employ circuit analysis and self-influence functions to evaluate the changing importance of each token throughout the reasoning process.<n>We demonstrate that the underlying circuits reveal a human-interpretable reasoning process used by the model.
  arXiv  Detail & Related papers  (2025-02-13T07:19:05Z)
• MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models [19.81485079689837]
  We evaluate large language models' capabilities in inductive and deductive stages.<n>We find that the models tend to consistently conduct correct deduction without correct inductive rules.<n>In the inductive reasoning process, the model tends to focus on observed facts that are close to the current test example in feature space.
  arXiv  Detail & Related papers  (2024-10-12T14:12:36Z)
• Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference [13.59675117792588]
  Recent studies on language models (LMs) have sparked a debate on whether they can learn systematic inferential principles.<n>This paper presents a mechanistic interpretation of syllogistic inference.
  arXiv  Detail & Related papers  (2024-08-16T07:47:39Z)
• An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models [99.31449616860291]
  Modern language models (LMs) can learn to perform new tasks in different ways. In instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly. In instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description.
  arXiv  Detail & Related papers  (2024-04-03T19:31:56Z)
• Language Models can be Logical Solvers [99.40649402395725]
  We introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers.
  arXiv  Detail & Related papers  (2023-11-10T16:23:50Z)
• Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement [92.61557711360652]
  Language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks. We conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement. We reveal several discrepancies between the inductive reasoning processes of LMs and humans, shedding light on both the potentials and limitations of using LMs in inductive reasoning tasks.
  arXiv  Detail & Related papers  (2023-10-12T17:51:10Z)
• 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)

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.