Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913543946764288 |
|---|---|
| author | Yang, Ling Yu, Zhaochen Zhang, Tianjun Cao, Shiyi Xu, Minkai Zhang, Wentao Gonzalez, Joseph E. Cui, Bin |
| author_facet | Yang, Ling Yu, Zhaochen Zhang, Tianjun Cao, Shiyi Xu, Minkai Zhang, Wentao Gonzalez, Joseph E. Cui, Bin |
| contents | We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Notably, we find that our Llama3-8B+BoT has the potential to surpass Llama3-70B model. Our project is available at: https://github.com/YangLing0818/buffer-of-thought-llm |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04271 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models Yang, Ling Yu, Zhaochen Zhang, Tianjun Cao, Shiyi Xu, Minkai Zhang, Wentao Gonzalez, Joseph E. Cui, Bin Computation and Language We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Notably, we find that our Llama3-8B+BoT has the potential to surpass Llama3-70B model. Our project is available at: https://github.com/YangLing0818/buffer-of-thought-llm |
| title | Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.04271 |