mlsanityData to 7 Oct 2026

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

arXiv 2607.08018 ↗First posted 9 Jul 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 9 Jul 2026.

Builds on

24 of 36 references.

References · 24

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  8. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  9. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  10. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  11. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  12. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
12 more
  1. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  2. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  3. 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoningcited by 195
  4. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  5. 2023Large Language Models as Analogical Reasonerscited by 107
  6. 2023System 2 Attention (is something you might need too)cited by 85
  7. 2023Thread of Thought Unraveling Chaotic Contextscited by 71
  8. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  9. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  10. 2024EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summariescited by 33
  11. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 20
  12. 2025Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMscited by 17

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge
  2. 2026LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  4. 2024Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning
  5. 2022Measuring and Narrowing the Compositionality Gap in Language Models
  6. 2024Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models
  7. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
  8. 2026KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models