Logical Misconceptions, Pragmatic Insufficiencies in LLMs and How to Fix Them

2026/07/23 by Nicholas Asher, Swarnadeep Bhar
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Logic, Reasoning, and Knowledge

paper · pdf · doi:10.1007/s11245-026-10459-6

Abstract

Abstract Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. Extending on the arguments of Asher and Bhar (2024), we show that logical incoherencies follow from an LLM’s computation of its internal representations, in particular from an LLM’s failure to take account of the different roles that different expressions may play in determining content. Linguistics and logicians have shown the importance of the fact that logical operators provide a structure on which to compute content recursively. We extend this view of logical tokens to structure at the discursive level with an eye to improving pragmatic reasoning as well as deductive reasoning. The key in reasoning is that these structures introduce operations over an LM’s latent representations that constrain how they may evolve . We show how LLMs can leverage those structures.

Citations

• Learning Semantic Structure through First-Order-Logic Translation
• Nebula: A discourse aware Minecraft Builder
• Llamipa: An Incremental Discourse Parser
• Faithful Logical Reasoning via Symbolic Chain-of-Thought
• Limits for Learning with Language Models
• Language models are not naysayers: An analysis of language models on negation benchmarks
• On the Planning Abilities of Large Language Models : A Critical Investigation
• Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
• Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation
• Correcting The Guide to Objective Chance
• The Semantic Conception of Truth: and the Foundations of Semantics
• Truth and meaning

Related

• Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study
• What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models
• Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
• Do Large Language Models Understand Logic or Just Mimick Context?
• Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs