arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.14158cs.CL
收藏

TOOLVERIFIER:通过自我验证泛化到新工具

TOOLVERIFIER: Generalization to New Tools via Self-Verification

Meta;University of California San Diego(加利福尼亚大学圣迭戈分校)

Dheeraj Mekala, Jason Weston, Jack Lanchantin, Roberta Raileanu, Maria Lomeli, Jingbo Shang, Jane Dwivedi-Yu

AI总结:

本文提出TOOLVERIFIER自我验证方法,通过对比性提问区分候选工具,在ToolBench的4个任务、17个未见工具上平均提升22%,实现对新工具的稳健泛化。

摘要:

教会语言模型使用工具是构建通用助手的重要里程碑,但仍是一个开放问题。虽然通过微调学习使用特定工具已取得显著进展,但语言模型在仅凭少量演示的情况下,仍难以学会稳健地使用新工具。在这项工作中,我们引入了一种自我验证方法,通过在(1)工具选择和(2)参数生成过程中自我提出对比性问题来区分相近的候选工具。我们使用Llama-2 70B为这一目标构建了合成的高质量自生成数据,并计划公开发布。在ToolBench基准的4个任务(包含17个未见过的工具)上进行的大量实验表明,与少样本基线相比,平均改进了22%,即使在候选工具之间差异非常细微的场景中也是如此。

英文摘要:

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% over few-shot baselines, even in scenarios where the distinctions between candidate tools are finely nuanced.

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。

↑