GEAR: 利用可泛化且高效的工具解析增强语言模型
GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution
AI总结：
针对现有工具增强LLM依赖特定任务演示、泛化性差且计算成本高的问题，提出将工具锚定委派给SLM、执行委派给LLM的GEAR算法，在多任务数据集上验证其兼具高效性与更高准确率。
摘要：
为大语言模型（LLM）增加外部工具使用能力可提升其在多种任务上的表现。但现有研究过度依赖特定任务的工具使用演示，这限制了模型的泛化性，且因需要多次调用大规模LLM导致计算成本较高。我们提出GEAR，这是一种计算高效的查询-工具锚定算法，可泛化到各类需要工具使用的任务，且无需依赖特定任务的演示。GEAR通过将工具锚定和执行分别委派给小语言模型（SLM）和LLM来提升效率，同时在问题和答案层面利用基于语义与模式的评估实现可泛化的工具锚定。我们在6个下游任务的14个数据集上评估了GEAR，证明其对新任务、新工具以及不同SLM都具备强泛化性。尽管效率更高，与以往使用LLM提示的策略相比，GEAR的工具锚定精度更高，从而在降低计算成本的同时提升了下游任务准确率。例如，我们证明经GEAR增强的GPT-J和GPT-3因工具使用更优，表现优于对应的工具增强基线模型。
英文摘要：
Augmenting large language models (LLM) to use external tools enhances their performance across a variety of tasks. However, prior works over-rely on task-specific demonstration of tool use that limits their generalizability and computational cost due to making many calls to large-scale LLMs. We introduce GEAR, a computationally efficient query-tool grounding algorithm that is generalizable to various tasks that require tool use while not relying on task-specific demonstrations. GEAR achieves better efficiency by delegating tool grounding and execution to small language models (SLM) and LLM, respectively; while leveraging semantic and pattern-based evaluation at both question and answer levels for generalizable tool grounding. We evaluate GEAR on 14 datasets across 6 downstream tasks, demonstrating its strong generalizability to novel tasks, tools and different SLMs. Despite offering more efficiency, GEAR achieves higher precision in tool grounding compared to prior strategies using LLM prompting, thus improving downstream accuracy at a reduced computational cost. For example, we demonstrate that GEAR-augmented GPT-J and GPT-3 outperform counterpart tool-augmented baselines because of better tool use.
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。
