通过内在自我批评增强大语言模型的规划能力
Enhancing LLM Planning Capabilities through Intrinsic Self-Critique
AI总结：
通过内在自我批评方法提升大语言模型的规划能力，实现Blocksworld、Logistics和Mini-grid数据集上的性能改进。
摘要：
我们展示了一种方法，使大语言模型能够批判其自身答案，以提高性能，从而在已建立的规划基准上取得显著改进。尽管先前研究对利用自我批评方法的LLM有效性持怀疑态度，但我们通过内在自我批评在Blocksworld领域规划数据集上实现了显著性能提升，无需外部来源如验证器。我们还展示了在Logistics和Mini-grid数据集上类似的改进，超过了强基线准确性。我们采用少量学习技术，并逐步扩展到多shot方法作为基本方法，并证明通过迭代过程进行纠正和改进，可以在该已具竞争力的方法上获得显著提升。我们展示了自我批评如何显著提升规划性能。我们的实证结果在所考虑的模型类别中展示了新的最先进的结果，即2024年10月的LLM模型检查点。我们的主要关注点在于方法本身，展示了无论具体模型版本如何，内在自我改进能力都适用，并且我们相信将此方法应用于更复杂的搜索技术和更强大的模型将带来更好的性能。
英文摘要：
We demonstrate an approach for LLMs to critique their \emph{own} answers with the goal of enhancing their performance that leads to significant improvements over established planning benchmarks. Despite the findings of earlier research that has cast doubt on the effectiveness of LLMs leveraging self critique methods, we show significant performance gains on planning datasets in the Blocksworld domain through intrinsic self-critique, without external source such as a verifier. We also demonstrate similar improvements on Logistics and Mini-grid datasets, exceeding strong baseline accuracies. We employ a few-shot learning technique and progressively extend it to a many-shot approach as our base method and demonstrate that it is possible to gain substantial improvement on top of this already competitive approach by employing an iterative process for correction and refinement. We illustrate how self-critique can significantly boost planning performance. Our empirical results present new state-of-the-art on the class of models considered, namely LLM model checkpoints from October 2024. Our primary focus lies on the method itself, demonstrating intrinsic self-improvement capabilities that are applicable regardless of the specific model version, and we believe that applying our method to more complex search techniques and more capable models will lead to even better performance.
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。
