Alignment for Efficient Tool Calling of Large Language Models
This addresses the challenge of tradeoffs between performance, speed, and cost in tool learning for LLMs, though it appears incremental as it builds on existing alignment and estimation methods.
The paper tackles the problem of aligning large language models (LLMs) with their knowledge boundaries to improve tool invocation decisions, resulting in significant improvements in tool efficiency by reducing unnecessary tool usage.
Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces tradeoffs between performance, speed, and cost, with LLMs sometimes exhibiting overreliance and overconfidence in tool usage. This paper addresses the challenge of aligning LLMs with their knowledge boundaries to make more intelligent decisions about tool invocation. We propose a multi objective alignment framework that combines probabilistic knowledge boundary estimation with dynamic decision making, allowing LLMs to better assess when to invoke tools based on their confidence. Our framework includes two methods for knowledge boundary estimation, consistency based and absolute estimation, and two training strategies for integrating these estimates into the model decision making process. Experimental results on various tool invocation scenarios demonstrate the effectiveness of our framework, showing significant improvements in tool efficiency by reducing unnecessary tool usage.