T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step
This addresses the need for more detailed evaluation of LLMs' tool use for researchers and developers, though it is incremental as it builds on existing evaluation frameworks.
The paper tackles the problem of evaluating large language models' tool-utilization capability by decomposing it into sub-processes like instruction following and planning, introducing T-Eval for step-by-step assessment, and finds it provides fine-grained analysis consistent with outcome-oriented methods.
Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool-utilization capability of LLMs is still under-explored. In contrast to previous works that evaluate models holistically, we comprehensively decompose the tool utilization into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review. Based on that, we further introduce T-Eval to evaluate the tool utilization capability step by step. T-Eval disentangles the tool utilization evaluation into several sub-domains along model capabilities, facilitating the inner understanding of both holistic and isolated competency of LLMs. We conduct extensive experiments on T-Eval and in-depth analysis of various LLMs. T-Eval not only exhibits consistency with the outcome-oriented evaluation but also provides a more fine-grained analysis of the capabilities of LLMs, providing a new perspective in LLM evaluation on tool-utilization ability. The benchmark will be available at https://github.com/open-compass/T-Eval.