Knowledge Vector of Logical Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2604.23877v1
• Date: Sun, 26 Apr 2026 20:37:26 GMT
• Title: Knowledge Vector of Logical Reasoning in Large Language Models
• Abstract summary: We study the knowledge representations of three main forms of logical reasoning: deductive, inductive, and abductive reasoning.<n>Our analysis shows that each form of logical reasoning can be captured as a reasoning-specific knowledge vector in a linear representation space.<n>We propose to refine the knowledge representations of each reasoning type in LLMs to encourage complementarity between them.
• Score: 32.88383839778735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Logical reasoning serve as a central capability in LLMs and includes three main forms: deductive, inductive, and abductive reasoning. In this work, we study the knowledge representations of these reasoning types in LLMs and analyze the correlations among them. Our analysis shows that each form of logical reasoning can be captured as a reasoning-specific knowledge vector in a linear representation space, yet these vectors are largely independent of each other. Motivated by cognitive science theory that these subforms of logical reasoning interact closely in the human brain, as well as our observation that the reasoning process for one type can benefit from the reasoning chain produced by another, we further propose to refine the knowledge representations of each reasoning type in LLMs to encourage complementarity between them. To this end, we design a complementary subspace-constrained refinement framework, which introduces a complementary loss that enables each reasoning vector to leverage auxiliary knowledge from the others, and a subspace constraint loss that prevents erasure of their unique characteristics. Through steering experiments along reasoning vectors, we find that refined vectors incorporating complementary knowledge yield consistent performance gains. We also conduct a mechanism-interpretability analysis of each reasoning vector, revealing insights into the shared and specific features of different reasoning in LLMs.

Related papers

• Beyond representational alignment with brain-guided language models for robust reasoning [51.87370932573858]
  We show that large language models (LLMs) align with neural signals from reasoning-related regions.<n>Using a neural-predictivity metric, we find that LLMs explain a substantial fraction of the explainable variance in reasoning-related regions.<n>We propose a brain-guided framework: we steer model representations along directions induced by the joint structure of model and brain representations.
  arXiv  Detail & Related papers  (2026-06-10T10:22:49Z)
• The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes [55.42597391158023]
  This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology.<n>We introduce a structured taxonomy of reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning.<n>We synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross
  arXiv  Detail & Related papers  (2026-06-09T21:59:37Z)
• Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views [16.869958532486258]
  Large Language Models (LLMs) still struggle with multi-step logical reasoning.<n>We ask whether LLMs contain a shared internal logical subspace that simultaneously aligns natural-language and symbolic-language views.
  arXiv  Detail & Related papers  (2026-04-21T17:42:54Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• 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)
• Logical Reasoning in Large Language Models: A Survey [17.06712393613964]
  This survey synthesizes recent advancements in logical reasoning in large language models (LLMs)<n>It outlines the scope of logical reasoning in LLMs, its theoretical foundations, and the benchmarks used to evaluate reasoning proficiency.<n>The review concludes with future directions, emphasizing the need for further exploration to strengthen logical reasoning in AI systems.
  arXiv  Detail & Related papers  (2025-02-13T09:19:14Z)
• 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)
• 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)
• Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners [75.85554779782048]
  Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous successful applications, the underlying mechanism of such in-context capabilities still remains unclear. In this work, we hypothesize that the learned textitsemantics of language tokens do the most heavy lifting during the reasoning process.
  arXiv  Detail & Related papers  (2023-05-24T07:33:34Z)

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.