Summary of Optibench Meets Resocratic: Measure and Improve Llms For Optimization Modeling, by Zhicheng Yang et al.
OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
by Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, Jing Tang
First submitted to arxiv on: 13 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes OptiBench, a benchmark for evaluating large language models’ (LLMs) problem-solving abilities in mathematical reasoning and optimization. The benchmark contains realistic optimization problems with human-readable inputs and outputs, including linear and nonlinear programming with or without tabular data. To alleviate data scarcity and bridge the gap between open-source and closed-source LLMs, the paper also proposes a data synthesis method called ReSocratic. Experimental results show that ReSocratic-29k significantly improves the performance of open-source models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to test how well large language models can solve math problems. It makes a special set of problems that are like real-life scenarios, and it shows how these models do when they’re tested on these problems. The researchers also make a way to create more data for these models to learn from, which helps them get better at solving the math problems. |
Keywords
* Artificial intelligence * Optimization
