Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference

• URL: http://arxiv.org/abs/2408.08590v3
• Date: Sat, 21 Jun 2025 10:50:24 GMT
• Title: Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
• Authors: Geonhee Kim, Marco Valentino, André Freitas,
• Abstract summary: 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.
• Score: 13.59675117792588
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies on reasoning in language models (LMs) have sparked a debate on whether they can learn systematic inferential principles or merely exploit superficial patterns in the training data. To understand and uncover the mechanisms adopted for formal reasoning in LMs, this paper presents a mechanistic interpretation of syllogistic inference. Specifically, we present a methodology for circuit discovery aimed at interpreting content-independent and formal reasoning mechanisms. Through two distinct intervention methods, we uncover a sufficient and necessary circuit involving middle-term suppression that elucidates how LMs transfer information to derive valid conclusions from premises. Furthermore, we investigate how belief biases manifest in syllogistic inference, finding evidence of partial contamination from additional attention heads responsible for encoding commonsense and contextualized knowledge. Finally, we explore the generalization of the discovered mechanisms across various syllogistic schemes, model sizes and architectures. The identified circuit is sufficient and necessary for syllogistic schemes on which the models achieve high accuracy (>60%), with compatible activation patterns across models of different families. Overall, our findings suggest that LMs learn transferable content-independent reasoning mechanisms, but that, at the same time, such mechanisms do not involve generalizable and abstract logical primitives, being susceptible to contamination by the same world knowledge acquired during pre-training.

Related papers

• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping [1.145820303039203]
  This study focuses on addressing the current lack of a unified formal theoretical framework in machine learning.<n>universal definitions for model interpretability and ethical safety are proposed.<n>Three key theorems are proved: the equivalence of model interpretability and information recoverability, the assurance of ethical safety, and the estimation of generalization error.
  arXiv  Detail & Related papers  (2025-05-19T14:39:41Z)
• LogiDynamics: Unraveling the Dynamics of Logical Inference in Large Language Model Reasoning [49.58786377307728]
  This paper adopts an exploratory approach by introducing a controlled evaluation environment for analogical reasoning. We analyze the comparative dynamics of inductive, abductive, and deductive inference pipelines. We investigate advanced paradigms such as hypothesis selection, verification, and refinement, revealing their potential to scale up logical inference.
  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. We employ circuit analysis and self-influence functions to evaluate the changing importance of each token throughout the reasoning process. 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)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
  We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
  arXiv  Detail & Related papers  (2024-10-31T12:48:58Z)
• A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences [5.141416267381492]
  We consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. We investigate the effects of chain-of-thought reasoning, in-context learning, and supervised fine-tuning on syllogistic reasoning. Our results suggest that the behavior of pre-trained LLMs can be explained by cognitive science.
  arXiv  Detail & Related papers  (2024-06-17T08:59:04Z)
• Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers [49.80959223722325]
  We study the distinction between feed-forward and attention layers in large language models. We find that feed-forward layers tend to learn simple distributional associations such as bigrams, while attention layers focus on in-context reasoning.
  arXiv  Detail & Related papers  (2024-06-05T08:51:08Z)
• Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals [82.68757839524677]
  Interpretability research aims to bridge the gap between empirical success and our scientific understanding of large language models (LLMs) We propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms.
  arXiv  Detail & Related papers  (2024-02-18T17:26:51Z)
• Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention [53.896974148579346]
  Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. The enigmatic black-box'' nature of LLMs remains a significant challenge for interpretability, hampering transparent and accountable applications. We propose a novel methodology anchored in sparsity-guided techniques, aiming to provide a holistic interpretation of LLMs.
  arXiv  Detail & Related papers  (2023-12-22T19:55:58Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)
• Explainability for Large Language Models: A Survey [59.67574757137078]
  Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. This paper introduces a taxonomy of explainability techniques and provides a structured overview of methods for explaining Transformer-based language models.
  arXiv  Detail & Related papers  (2023-09-02T22:14:26Z)
• 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)
• Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability [30.76910454663951]
  Causal abstraction provides a theoretical foundation for mechanistic interpretability. Our contributions are generalizing the theory of causal abstraction from mechanism replacement to arbitrary mechanism transformation.
  arXiv  Detail & Related papers  (2023-01-11T20:42:41Z)
• Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge [91.15301779076187]
  We introduce verbalized knowledge into the minibatches of a BERT model during pre-training and evaluate how well the model generalizes to supported inferences. We find generalization does not improve over the course of pre-training, suggesting that commonsense knowledge is acquired from surface-level, co-occurrence patterns rather than induced, systematic reasoning.
  arXiv  Detail & Related papers  (2021-12-16T03:13:04Z)
• Abduction and Argumentation for Explainable Machine Learning: A Position Survey [2.28438857884398]
  This paper presents Abduction and Argumentation as two principled forms for reasoning. It fleshes out the fundamental role that they can play within Machine Learning.
  arXiv  Detail & Related papers  (2020-10-24T13:23:44Z)
• Plausible Reasoning about EL-Ontologies using Concept Interpolation [27.314325986689752]
  We propose an inductive mechanism which is based on a clear model-theoretic semantics, and can thus be tightly integrated with standard deductive reasoning. We focus on inference, a powerful commonsense reasoning mechanism which is closely related to cognitive models of category-based induction.
  arXiv  Detail & Related papers  (2020-06-25T14:19:41Z)
• Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [96.92252296244233]
  Large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is difficult to control. We show that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements. Our work paves a path towards open-domain systems that constantly improve by interacting with users who can instantly correct a model by adding simple natural language statements.
  arXiv  Detail & Related papers  (2020-06-11T17:02:20Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

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.