Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models

2026-07-08

AI Summary

This work addresses the inherent tension in large language models between compositional reasoning and knowledge retrieval, which are difficult to reconcile simultaneously. The authors propose Concrete Propositional Prompting (CPP), a novel framework that, for the first time, explicitly incorporates concrete propositional representations into prompt design. By structuring relevant factual propositions in a logically coherent manner, CPP seamlessly integrates logical composition with grounded knowledge without requiring model fine-tuning. The method demonstrates strong performance across diverse base models and parameter scales, achieving significant gains on medical reasoning benchmarks while remaining competitive on mathematical tasks. These results indicate that CPP effectively bridges the gap between compositional and knowledge-intensive reasoning, exhibiting both broad applicability and practical utility.

Abstract

LLMs often struggle to balance compositionality with knowledgeability, a challenge we define as Composition-Knowledge Dichotomy. To address this, we propose Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to questions. The results demonstrate that CPP significantly enhances reasoning performance, particularly in medical benchmarks where precise knowledge is paramount, while being competitive on math benchmarks where deductive reasoning is prioritized. Additional experiments reveal that CPP is scalable to various foundation models and parameter sizes, being a fundamental paradigm that bridges the gap between composition- and knowledge-based approaches. Consequently, CPP resolves the composition-knowledge dichotomy by providing a solid foundation for logically organized and factually grounded reasoning.

Problem

• Compositionality
• Knowledgeability
• Large Language Models
• Reasoning
• Composition-Knowledge Dichotomy

Innovation

• Concretized Proposition Prompting
• Composition-Knowledge Dichotomy
• Large Language Models
• Reasoning Framework
• Knowledge Integration