Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917585347411968 |
|---|---|
| author | Feng, Xidong Wan, Ziyu Wen, Muning McAleer, Stephen Marcus Wen, Ying Zhang, Weinan Wang, Jun |
| author_facet | Feng, Xidong Wan, Ziyu Wen, Muning McAleer, Stephen Marcus Wen, Ying Zhang, Weinan Wang, Jun |
| contents | Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a result, these methods will not work in domains where the pre-trained LLM does not have enough knowledge to serve as an effective value function or in domains that require long-horizon planning. To address these limitations, we present an AlphaZero-like tree-search learning framework for LLMs (termed TS-LLM), systematically illustrating how tree-search with a learned value function can guide LLM decoding. TS-LLM distinguishes itself in two key ways. (1) Leveraging a learned value function and AlphaZero-like algorithms, our approach can be generally adaptable to a wide range of tasks, language models of any size, and tasks of varying search depths. (2) Our approach can guide LLMs during both inference and training, iteratively improving the LLM. Empirical results across reasoning, planning, alignment, and decision-making tasks show that TS-LLM outperforms existing approaches and can handle trees with a depth of 64. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_17179 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training Feng, Xidong Wan, Ziyu Wen, Muning McAleer, Stephen Marcus Wen, Ying Zhang, Weinan Wang, Jun Machine Learning Artificial Intelligence Computation and Language Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a result, these methods will not work in domains where the pre-trained LLM does not have enough knowledge to serve as an effective value function or in domains that require long-horizon planning. To address these limitations, we present an AlphaZero-like tree-search learning framework for LLMs (termed TS-LLM), systematically illustrating how tree-search with a learned value function can guide LLM decoding. TS-LLM distinguishes itself in two key ways. (1) Leveraging a learned value function and AlphaZero-like algorithms, our approach can be generally adaptable to a wide range of tasks, language models of any size, and tasks of varying search depths. (2) Our approach can guide LLMs during both inference and training, iteratively improving the LLM. Empirical results across reasoning, planning, alignment, and decision-making tasks show that TS-LLM outperforms existing approaches and can handle trees with a depth of 64. |
| title | Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2309.17179 |