Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
- URL: http://arxiv.org/abs/2406.04271v2
- Date: Mon, 14 Oct 2024 07:12:27 GMT
- Title: Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
- Authors: Ling Yang, Zhaochen Yu, Tianjun Zhang, Shiyi Cao, Minkai Xu, Wentao Zhang, Joseph E. Gonzalez, Bin Cui,
- Abstract summary: Buffer of Thoughts (BoT) is a novel and versatile thought-augmented reasoning approach.
We propose meta-buffer to store a series of informative high-level thoughts.
For each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures.
- Score: 65.48185395952788
- License:
- Abstract: 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
Related papers
- Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths [69.39559168050923]
We introduce Reasoning Paths Optimization (RPO), which enables learning to reason and explore from diverse paths.
Our approach encourages favorable branches at each reasoning step while penalizing unfavorable ones, enhancing the model's overall problem-solving performance.
We focus on multi-step reasoning tasks, such as math word problems and science-based exam questions.
arXiv Detail & Related papers (2024-10-07T06:37:25Z) - Can Github issues be solved with Tree Of Thoughts? [0.0]
This research introduces the application of the Tree of Thoughts (ToT) language model reasoning framework for enhancing the decision-making and problem-solving abilities of LLMs.
We experimentally deploy ToT in tackling a Github issue contained within an instance of the SWE-bench.
arXiv Detail & Related papers (2024-05-20T11:05:56Z) - Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models [102.72940700598055]
In reasoning tasks, even a minor error can cascade into inaccurate results.
We develop a method that avoids introducing external resources, relying instead on perturbations to the input.
Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks.
arXiv Detail & Related papers (2024-03-04T16:21:54Z) - Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models [73.79091519226026]
Uncertainty of Thoughts (UoT) is an algorithm to augment large language models with the ability to actively seek information by asking effective questions.
In experiments on medical diagnosis, troubleshooting, and the 20 Questions game, UoT achieves an average performance improvement of 38.1% in the rate of successful task completion.
arXiv Detail & Related papers (2024-02-05T18:28:44Z) - Large-Batch, Iteration-Efficient Neural Bayesian Design Optimization [37.339567743948955]
We present a novel Bayesian optimization framework specifically tailored to address the limitations of BO.
Our key contribution is a highly scalable, sample-based acquisition function that performs a non-dominated sorting of objectives.
We show that our acquisition function in combination with different Bayesian neural network surrogates is effective in data-intensive environments with a minimal number of iterations.
arXiv Detail & Related papers (2023-06-01T19:10:57Z) - Tree of Thoughts: Deliberate Problem Solving with Large Language Models [52.31950122881687]
We introduce a new framework for language model inference, Tree of Thoughts (ToT)
ToT generalizes over the popular Chain of Thought approach to prompting language models.
Our experiments show that ToT significantly enhances language models' problem-solving abilities.
arXiv Detail & Related papers (2023-05-17T23:16:17Z) - Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them [108.54545521369688]
We focus on a suite of 23 challenging BIG-Bench tasks which we call BIG-Bench Hard (BBH)
We find that applying chain-of-thought (CoT) prompting to BBH tasks enables PaLM to surpass the average human-rater performance on 10 of the 23 tasks, and Codex to surpass the average human-rater performance on 17 of the 23 tasks.
arXiv Detail & Related papers (2022-10-17T17:08:26Z) - MBORE: Multi-objective Bayesian Optimisation by Density-Ratio Estimation [0.01652719262940403]
optimisation problems often have multiple conflicting objectives that can be computationally and/or financially expensive.
Mono-surrogate Bayesian optimisation (BO) is a popular model-based approach for optimising such black-box functions.
We extend previous work on BO by density-ratio estimation (BORE) to the multi-objective setting.
arXiv Detail & Related papers (2022-03-31T09:27:59Z) - Scalable Combinatorial Bayesian Optimization with Tractable Statistical
models [44.25245545568633]
We study the problem of optimizing blackbox functions over Relaxation spaces (e.g., sets, sequences, trees, and graphs)
Based on recent advances in submodular relaxation, we study an approach as Parametrized Submodular (PSR) towards the goal of improving the scalability and accuracy of solving AFO problems for BOCS model.
Experiments on diverse benchmark problems show significant improvements with PSR for BOCS model.
arXiv Detail & Related papers (2020-08-18T22:56:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.