Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs

2025-10-30

AI Summary

Large language models (LLMs) exhibit significant limitations in understanding implicit meaning. To address this, we propose a pragmatics-enhanced prompting method that integrates classical pragmatic frameworks—such as Grice’s Cooperative Principle and Relevance Theory—into in-context learning and chain-of-thought reasoning via lightweight prompts (e.g., theory names or concise definitions), thereby guiding multi-step semantic inference. Unlike computationally intensive fine-tuning or structured knowledge injection, our approach achieves interpretable, theory-guided reasoning solely through prompt engineering. Experiments across multiple implicit meaning understanding benchmarks demonstrate that our method improves LLM accuracy by up to 9.6%. Notably, even minimal prompts—using only theory names—yield consistent performance gains of 1–3%, underscoring the efficacy and practicality of pragmatic theories as cognitive scaffolds for implicit reasoning.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The ability to accurately interpret implied meanings plays a crucial role in human communication and language use, and language models are also expected to possess this capability. This study demonstrates that providing language models with pragmatic theories as prompts is an effective in-context learning approach for tasks to understand implied meanings. Specifically, we propose an approach in which an overview of pragmatic theories, such as Gricean pragmatics and Relevance Theory, is presented as a prompt to the language model, guiding it through a step-by-step reasoning process to derive a final interpretation. Experimental results showed that, compared to the baseline, which prompts intermediate reasoning without presenting pragmatic theories (0-shot Chain-of-Thought), our methods enabled language models to achieve up to 9.6% higher scores on pragmatic reasoning tasks. Furthermore, we show that even without explaining the details of pragmatic theories, merely mentioning their names in the prompt leads to a certain performance improvement (around 1-3%) in larger models compared to the baseline.

Problem

• Enhancing LLMs' interpretation of implied meanings
• Using pragmatic theories as prompts for reasoning
• Improving performance on pragmatic reasoning tasks

Innovation

• Using pragmatic theories as prompts for LLMs
• Step-by-step reasoning guided by Gricean pragmatics
• Mentioning theory names improves model performance