Saved in:
Bibliographic Details
Main Authors: Chen, Qiqi, Wang, Xinpeng, Mondorf, Philipp, Hedderich, Michael A., Plank, Barbara
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.17820
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914987151196160
author Chen, Qiqi
Wang, Xinpeng
Mondorf, Philipp
Hedderich, Michael A.
Plank, Barbara
author_facet Chen, Qiqi
Wang, Xinpeng
Mondorf, Philipp
Hedderich, Michael A.
Plank, Barbara
contents Tree of Thoughts (ToT) is a reasoning strategy for Large Language Models (LLMs) that employs a generator to suggest reasoning steps and a discriminator to decide which steps to implement. ToT demonstrates strong performance on reasoning tasks, often surpassing simple methods such as Input-Output (IO) prompting and Chain-of-Thought (CoT) reasoning. However, ToT does not consistently outperform such simpler methods across all models, leaving large knowledge gaps on the conditions under which ToT is most beneficial. In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial. We find that the generator plays a more critical role than the discriminator in driving the success of ToT. Scaling the generator leads to notable improvements in ToT performance, even when using a smaller model as the discriminator, whereas scaling the discriminator with a fixed generator yields only marginal gains. Our results show that models across different scales exhibit comparable discrimination capabilities, yet differ significantly in their generative performance for ToT.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17820
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
Chen, Qiqi
Wang, Xinpeng
Mondorf, Philipp
Hedderich, Michael A.
Plank, Barbara
Computation and Language
Tree of Thoughts (ToT) is a reasoning strategy for Large Language Models (LLMs) that employs a generator to suggest reasoning steps and a discriminator to decide which steps to implement. ToT demonstrates strong performance on reasoning tasks, often surpassing simple methods such as Input-Output (IO) prompting and Chain-of-Thought (CoT) reasoning. However, ToT does not consistently outperform such simpler methods across all models, leaving large knowledge gaps on the conditions under which ToT is most beneficial. In this paper, we analyze the roles of the generator and discriminator separately to better understand the conditions when ToT is beneficial. We find that the generator plays a more critical role than the discriminator in driving the success of ToT. Scaling the generator leads to notable improvements in ToT performance, even when using a smaller model as the discriminator, whereas scaling the discriminator with a fixed generator yields only marginal gains. Our results show that models across different scales exhibit comparable discrimination capabilities, yet differ significantly in their generative performance for ToT.
title Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
topic Computation and Language
url https://arxiv.org/abs/2410.17820