Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |