TOOLVERIFIER: Generalization to New Tools via Self-Verification
CoRR(2024)
摘要
Teaching language models to use tools is an important milestone towards
building general assistants, but remains an open problem. While there has been
significant progress on learning to use specific tools via fine-tuning,
language models still struggle with learning how to robustly use new tools from
only a few demonstrations. In this work we introduce a self-verification method
which distinguishes between close candidates by self-asking contrastive
questions during (1) tool selection; and (2) parameter generation. We construct
synthetic, high-quality, self-generated data for this goal using Llama-2 70B,
which we intend to release publicly. Extensive experiments on 4 tasks from the
ToolBench benchmark, consisting of 17 unseen tools, demonstrate an average
improvement of 22
distinctions between candidate tools are finely nuanced.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要