Learning to Plan with Natural Language
This addresses the issue of factual errors and incompleteness in LLM-generated plans for complex tasks, offering a transferable solution for enhancing reasoning performance, though it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of generating high-quality task plans for Large Language Models (LLMs) to improve performance on complex reasoning tasks, proposing a Learning to Plan method that iteratively updates plans using error feedback and demonstrates effectiveness across five reasoning tasks on 8 datasets, with analysis showing transferability to other LLMs.
Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks. For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step. LLMs can directly generate task plans, but these plans may still contain factual errors or are incomplete. A high-quality task plan contains correct step-by-step solutions for solving all situations and behavioral instructions for avoiding mistakes. To obtain it, we propose the Learning to Plan method, which involves two phases: (1) In the first learning task plan phase, it iteratively updates the task plan with new step-by-step solutions and behavioral instructions, which are obtained by prompting LLMs to derive from training error feedback. (2) In the subsequent test phase, the LLM uses the learned task plan to guide the inference of LLM on the test set. We demonstrate the effectiveness of our method on the five different reasoning type tasks (8 datasets). Further, our analysis experiment shows that the task plan learned by one LLM can directly guide another LLM to improve its performance, which reveals a new transfer learning paradigm. We release the code at \url{https://github.com/Eureka6174/LearnNLPlan}