mkhalifa/flan-t5-large-mathqa

GRACE: Discriminator-Guided Chain-of-Thought Reasoning

This repository contains a fine-tuned FLAN-T5 model as presented in the paper GRACE: Discriminator-Guided Chain-of-Thought Reasoning.

Model Description

GRACE (Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator) is a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps. It employs a step-level verifier or discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates based on their correctness. This specific checkpoint serves as the generator model fine-tuned for reasoning tasks.

• Repository: https://github.com/mukhal/grace
• Paper: GRACE: Discriminator-Guided Chain-of-Thought Reasoning

Citation

If you use this model or code, please consider citing the following paper:

@article{khalifa2023grace,
  title={Grace: Discriminator-guided chain-of-thought reasoning},
  author={Khalifa, Muhammad and Logeswaran, Lajanugen and Lee, Moontae and Lee, Honglak and Wang, Lu},
  journal={arXiv preprint arXiv:2305.14934},
  year={2023}
}