Combining Constraint Programming Reasoning with Large Language Model Predictions
CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）
Florian Régin, Elisabetta De Maria, Alexandre Bonlarron
备注：
To appear at The 30th International Conference on Principles and Practice of Constraint Programming (CP 2024)
发表信息：
In 30th International Conference on Principles and Practice of Constraint Programming (CP 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 307, pp. 25:1-25:18, Schloss Dagstuhl - Leibniz-Zentrum fur Informatik (2024)
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.
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming
Carnegie Mellon University（卡内基梅隆大学）；University of Pennsylvania（宾夕法尼亚大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Petuum Inc.（Petuum公司）
astra-langchain4j: Experiences Combining LLMs and Agent Programming
School of Computer Science, University College Dublin, Ireland（都柏林大学计算机科学学院）；School of Computer Science, University of St.Gallen, St. Gallen, Switzerland（圣加尔登大学计算机科学学院）
MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning
Fudan University（复旦大学）；MYbank, Ant Group（蚂蚁集团MYbank）；School of Computer Science, Fudan University（复旦大学计算机学院）；School of Data Science, Fudan University（复旦大学数据科学学院）
University of Technology Sydney（悉尼科技大学）；The University of Sydney（悉尼大学）；CSIRO（澳大利亚联邦科学与工业研究组织）；ELLIS Institute Finland（芬兰ELLIS研究所）；University of Turku（图尔库大学）
What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
State Key Laboratory of Cognitive Intelligence, University of Science（认知智能国家重点实验室，科学大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Centerce（人工智能研究院，合肥综合性国家科学中心）；Individual Researcher（个人研究员）；Zhejiang University, Hangzhou, China（浙江大学，杭州，中国）
Are Language Models Efficient Reasoners? A Perspective from Logic Programming
ETH Zürich（苏黎世联邦理工学院）；MPI for Intelligent Systems, Tübingen（智能系统马克斯·普朗克研究所）；EPFL（苏黎世联邦理工学院）；Idiap Research Institute（Idiap研究机构）；Purdue University（普渡大学）
