GRACE: Discriminator-Guided Chain-of-Thought Reasoning

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Submission Type: Regular Long Paper

Submission Track: Question Answering

Submission Track 2: Natural Language Generation

Keywords: chain-of-thought, guided decoding, math reasoning, symbolic reasoning, multi-step reasoning, large language models

TL;DR: A decoding method to guide multi-step reasoning at the step-level using a trained correctness discriminator model

Abstract:

In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies that optimize for solution likelihood often yield incorrect solutions.
To address this issue, we propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE), a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps.
GRACE employs a 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.
Importantly, GRACE only requires sampling from the LM, without the need for LM training or fine-tuning.
Using models from FLAN-T5 and LLaMA families, we evaluate GRACE over four math and two symbolic reasoning tasks, where it exhibits substantial performance gains compared to greedy decoding, verifiers, and self-consistency in most settings. When further combined with self-consistency, GRACE outperforms all the baselines by sizeable margins. Human and LLM evaluations over GSM8K show that GRACE not only improves the final answer accuracy but also the correctness of the intermediate reasoning.

Submission Number: 4059