CRISP：基于可解释步骤化计划的复杂推理
CRISP: Complex Reasoning with Interpretable Step-based Plans
AI总结：
本文挑战LLMs仅靠少样本提示即可生成有效计划的假设，提出多领域高级计划数据集CRISP，通过微调小模型生成更高质量计划，显著优于CoT推理且具备跨领域泛化能力。
摘要：
大型语言模型（LLMs）的最新进展凸显了更强推理能力的需求，以有效解决复杂问题。尽管思维链（Chain-of-Thought, CoT）推理向前迈出了一步，但在许多领域它仍然不够。一个有前景的替代方案是生成显式的高级计划，但现有方法很大程度上假设LLMs能仅通过少样本提示产生有效计划，而无需额外训练。在本工作中，我们挑战这一假设，并引入CRISP（Complex Reasoning with Interpretable Step-based Plans，基于可解释步骤化计划的复杂推理），一个用于数学推理和代码生成的多领域高级计划数据集。CRISP中的计划是自动生成并经过严格验证的——内在上使用LLM作为评判者，外在上通过评估其对下游任务性能的影响来验证。我们证明，在CRISP上微调一个小模型使其能生成比使用少样本提示的大得多的模型更高质量的计划，同时显著优于思维链推理。此外，我们的域外评估显示，在一个领域上微调可改善另一领域的计划生成，突显了所学规划能力的泛化性。
英文摘要：
Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for many domains. A promising alternative is explicit high-level plan generation, but existing approaches largely assume that LLMs can produce effective plans through few-shot prompting alone, without additional training. In this work, we challenge this assumption and introduce CRISP (Complex Reasoning with Interpretable Step-based Plans), a multi-domain dataset of high-level plans for mathematical reasoning and code generation. The plans in CRISP are automatically generated and rigorously validated--both intrinsically, using an LLM as a judge, and extrinsically, by evaluating their impact on downstream task performance. We demonstrate that fine-tuning a small model on CRISP enables it to generate higher-quality plans than much larger models using few-shot prompting, while significantly outperforming Chain-of-Thought reasoning. Furthermore, our out-of-domain evaluation reveals that fine-tuning on one domain improves plan generation in the other, highlighting the generalizability of learned planning capabilities.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
