OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

• URL: http://arxiv.org/abs/2407.09887v3
• Date: Tue, 8 Oct 2024 16:27:18 GMT
• Title: OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
• Authors: Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, Jing Tang,
• Abstract summary: Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning. We propose OptiBench, a benchmark for End-to-end optimization problem-solving with human-readable inputs and outputs.
• Score: 62.19438812624467
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning. Solving realistic optimization (OPT) problems in application scenarios requires advanced and applied mathematics ability. However, current OPT benchmarks that merely solve linear programming are far from complex realistic situations. In this work, we propose OptiBench, a benchmark for End-to-end optimization problem-solving with human-readable inputs and outputs. OptiBench contains rich optimization problems, including linear and nonlinear programming with or without tabular data, which can comprehensively evaluate LLMs' solving ability. In our benchmark, LLMs are required to call a code solver to provide precise numerical answers. Furthermore, to alleviate the data scarcity for optimization problems, and to bridge the gap between open-source LLMs on a small scale (e.g., Llama-3-8b) and closed-source LLMs (e.g., GPT-4), we further propose a data synthesis method namely ReSocratic. Unlike general data synthesis methods that proceed from questions to answers, \ReSocratic first incrementally synthesizes formatted optimization demonstration with mathematical formulations step by step and then back-translates the generated demonstrations into questions. Based on this, we synthesize the ReSocratic-29k dataset. We further conduct supervised fine-tuning with ReSocratic-29k on multiple open-source models. Experimental results show that ReSocratic-29k significantly improves the performance of open-source models.

Related papers

• LLM-based Optimization of Compound AI Systems: A Survey [64.39860384538338]
  In a compound AI system, components such as an LLM call, a retriever, a code interpreter, or tools are interconnected. Recent advancements enable end-to-end optimization of these parameters using an LLM. This paper presents a survey of the principles and emerging trends in LLM-based optimization of compound AI systems.
  arXiv  Detail & Related papers  (2024-10-21T18:06:25Z)
• LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch [16.174567164068037]
  We propose a unified learning-based framework called LLMOPT to boost optimization generalization. LLMOPT constructs the introduced five-element formulation as a universal model for learning to define diverse optimization problem types. We evaluate the optimization generalization ability of LLMOPT and compared methods across six real-world datasets.
  arXiv  Detail & Related papers  (2024-10-17T04:37:37Z)
• OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale [16.33736498565436]
  We introduce a Large Language Model (LLM)-based system designed to formulate and solve linear programming problems from their natural language descriptions. Our system is capable of developing mathematical models, writing and debugning solver code, evaluating the generated solutions, and improving efficiency and correctness of its model and code. Experiments demonstrate that OptiMUS-0.3 outperforms existing state-of-the-art methods on easy datasets by more than 12% and on hard datasets by more than 8%.
  arXiv  Detail & Related papers  (2024-07-29T01:31:45Z)
• Solving General Natural-Language-Description Optimization Problems with Large Language Models [34.50671063271608]
  We propose a novel framework called OptLLM that augments LLMs with external solvers. OptLLM accepts user queries in natural language, convert them into mathematical formulations and programming codes, and calls the solvers to calculate the results. Some features of OptLLM framework have been available for trial since June 2023.
  arXiv  Detail & Related papers  (2024-07-09T07:11:10Z)
• OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models [21.519880445683107]
  This paper introduces OptiMUS, a Large Language Model (LL)M-based agent designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. OptiMUS can develop mathematical models, write and debug solver code, evaluate the generated solutions, and improve its model and code based on these evaluations. Experiments demonstrate that OptiMUS outperforms existing state-of-the-art methods on easy datasets by more than $20%$ and on hard datasets by more than $30%$.
  arXiv  Detail & Related papers  (2024-02-15T18:19:18Z)
• OptiMUS: Optimization Modeling Using MIP Solvers and large language models [21.519880445683107]
  We introduce OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve MILP problems from their natural language descriptions. To benchmark our agent, we present NLP4LP, a novel dataset of linear programming (LP) and mixed integer linear programming (MILP) problems. Our experiments demonstrate that OptiMUS solves nearly twice as many problems as a basic LLM prompting strategy.
  arXiv  Detail & Related papers  (2023-10-09T19:47:03Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• Large Language Models as Optimizers [106.52386531624532]
  We propose Optimization by PROmpting (OPRO), a simple and effective approach to leverage large language models (LLMs) as prompts. In each optimization step, the LLM generates new solutions from the prompt that contains previously generated solutions with their values. We demonstrate that the best prompts optimized by OPRO outperform human-designed prompts by up to 8% on GSM8K, and by up to 50% on Big-Bench Hard tasks.
  arXiv  Detail & Related papers  (2023-09-07T00:07:15Z)
• SatLM: Satisfiability-Aided Language Models Using Declarative Prompting [68.40726892904286]
  We propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of large language models (LLMs) We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm.
  arXiv  Detail & Related papers  (2023-05-16T17:55:51Z)
• Learning to Optimize: A Primer and A Benchmark [94.29436694770953]
  Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization.
  arXiv  Detail & Related papers  (2021-03-23T20:46:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.