三思而后行：迈向大型语言模型的决策感知与可泛化工具使用
Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models
AI总结：
本文提出决策感知与可泛化工具使用框架DEER，通过自动生成多决策分支样本和新颖工具采样策略，提升开源LLMs处理多样查询的灵活性与对未见工具的泛化能力，显著优于基线。
摘要：
工具增强的大型语言模型（LLMs）在获取最新知识和缓解幻觉问题方面正受到广泛关注。如今，先进的闭源LLMs（如ChatGPT）通过提示和上下文学习技术展示了惊人的工具使用能力。为了赋予开源LLMs（如LLaMA）操作工具的能力，当前的努力主要集中在基于模板或基于token触发的工具使用上。然而，前者由于受限的工具交互而阻碍了LLMs处理多样化用户查询的灵活性，而后者由于工具使用学习基于任务和工具特定的数据集，限制了与新工具交互时的泛化能力。为了缓解这些问题，在本文中，我们提出了一个决策感知和可泛化的工具使用框架（DEER）。具体而言，我们首先通过自动生成管道构建具有多个决策分支的工具使用样本，从而激发LLMs在多样化场景下的决策意识。同时，我们提出了一种新颖的工具采样策略，以增强LLMs对未见工具的泛化能力。大量实验表明，我们提出的DEER是有效的，并在各种数据集上显著优于基线。
英文摘要：
Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising tool-usage capabilities through prompting and in-context learning techniques. To empower the capabilities of open-source LLMs (e.g., LLaMA) in manipulating tools, current efforts focus on either template-driven or token-triggered tool-usage. However, the former hampers LLMs' flexibility to address diverse user's queries due to constrained tool interactions, while the latter limits the generalizability when engaging with new tools, since tool-usage learning is based on task- and tool-specific datasets. To alleviate these concerns, in this paper, we propose a decision-aware and generalizable tool-usage framework (DEER). Specifically, we first construct the tool-usage samples with multiple decision branches via an automatic generation pipeline, thereby inspiring the decision-making awareness of LLMs under diverse scenarios. Meanwhile, we propose a novel tool sampling strategy to enhance the generalizability of LLMs over unseen tools. Extensive experiments demonstrate that our proposed DEER is effective and significantly outperforms baselines across various datasets.
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。
