mlsanityData to 7 Oct 2026

Combining Constraint Programming Reasoning with Large Language Model Predictions

arXiv 2407.13490 ↗First posted 18 Jul 2024cs.CL cs.AIcited by 8

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Constraint Programming (CP) and Machine Learning (ML) face challenges in text generation due to CP's struggle with implementing "meaning'' and ML's difficulty with structural constraints. This paper proposes a solution by combining both approaches and embedding a Large Language Model (LLM) in CP. The LLM handles word generation and meaning, while CP manages structural constraints. This approach builds on GenCP, an improved version of On-the-fly Constraint Programming Search (OTFS) using LLM-generated domains. Compared to Beam Search (BS), a standard NLP method, this combined approach (GenCP with LLM) is faster and produces better results, ensuring all constraints are satisfied. This fusion of CP and ML presents new possibilities for enhancing text generation under constraints.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 20 of its 46 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

20 of 46 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  6. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  7. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 612
  8. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  9. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  10. 2021End-to-End Constrained Optimization Learning: A Surveycited by 154
  11. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  12. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 69
8 more
  1. 2020Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimizationcited by 63
  2. 2023Holy Grail 2.0: From Natural Language to Constraint Modelscited by 24
  3. 2022Why is constrained neural language generation particularly challenging?cited by 19
  4. 2023"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programmingcited by 19
  5. 2021Constrained Text Generation with Global Guidance -- Case Study on CommonGencited by 10
  6. 2023Constraints First: A New MDD-based Model to Generate Sentences Under Constraintscited by 4
  7. 2024Markov Constraint as Large Language Model Surrogatecited by 3
  8. 2024Intertwining CP and NLP: The Generation of Unreasonably Constrained Sentencescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024MCP-Solver: Integrating Language Models with Constraint Programming Systemscited by 9
  2. 2025Reliable Proof Generation with LLMs via Analogical Retrieval and Symbolic Verification: A Case Study in Euclidean Geometrycited by 7
  3. 2025CP-Agent: Agentic Constraint Programmingcited by 6
  4. 2025Distributed Multi-Agent Coordination Using Multi-Modal Foundation Modelscited by 3
  5. 2025Large Language Model Meets Constraint Propagationcited by 2
  6. 2026LLMs versus the Halting Problem: Characterizing Program Termination Reasoningcited by 2
  7. 2026Text2Model: Modeling Copilots for Text-to-Model Translationcited by 0
  8. 2026Improving Constraint Models with LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?
  2. 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
  3. 2026Learning and Enforcing Context-Sensitive Control for LLMs
  4. 2024Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
  5. 2024From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification
  6. 2025Applications of Large Language Model Reasoning in Feature Generation
  7. 2026Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process
  8. 2024Inference acceleration for large language models using "stairs" assisted greedy generation