ComputeGPT: A computational chat model for numerical problems
2023-05-08Code Available1· sign in to hype
Ryan Hardesty Lewis, Junfeng Jiao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/ryanhlewis/computegptevalOfficialIn papernone★ 11
Abstract
Language models are not accurate in numerical problems. Their architecture does not allow for anything less than a probabilistic next word. This paper introduces ComputeGPT: an approach of creating a chat model able to answer computational problems through running on-demand code. ComputeGPT converts each question to relevant code, runs the code, and returns the computed answer as part of the chat. We combine this approach with a local browser-based Python interpretation and fine-tuned prompts in order to achieve state-of-the-art efficiency on numerical problems and provide a suitable front-end and safe environment for the code to be executed in.