Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
This work addresses the challenge of enhancing LLM reasoning for complex problem-solving, representing an incremental improvement over existing prompting methods like Tree of Thoughts.
The paper tackles the problem of improving reasoning performance in Large Language Models (LLMs) for complex mathematical problems by introducing Boosting of Thoughts (BoT), an automated prompting framework that iteratively explores and self-evaluates reasoning steps, resulting in higher or comparable problem-solving rates than other advanced prompting approaches, as demonstrated with GPT-4 and Llama2.
The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts. Recent work, e.g., Tree of Thoughts, has pointed out the importance of exploration and self-evaluation in reasoning step selection for complex problem solving. In this paper, we present Boosting of Thoughts (BoT), an automated prompting framework for problem solving with LLMs by iteratively exploring and self-evaluating many trees of thoughts in order to acquire an ensemble of trial-and-error reasoning experiences, which will serve as a new form of prompting to solve the complex problem. Starting from a simple prompt without requiring examples, BoT iteratively explores and evaluates a large collection of reasoning steps, and more importantly, uses error analysis obtained from the LLM on them to explicitly revise prompting, which in turn enhances reasoning step generation, until a final answer is attained. Our experiments with GPT-4 and Llama2 across extensive complex mathematical problems demonstrate that BoT consistently achieves higher or comparable problem-solving rates than other advanced prompting approaches.