Computer ScienceICLR 2024
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-World APIs
Y. Qin, S. Liang, et al.
ToolLLM bridges the tool-use gap in open-source LLMs by introducing ToolBench — a ChatGPT-generated instruction-tuning dataset of 16,464 real-world RESTful APIs — along with a depth-first search decision-tree for richer reasoning, a neural API retriever, and the automatic evaluator ToolEval. This research, conducted by the authors listed in the <Authors> tag, produces ToolLLaMA with ChatGPT-comparable tool-use and strong zero-shot generalization.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Computer Science
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
N. Dainese, M. Alakuijala, et al.
Computer Science
Persuading large language models to comply with objectionable requests
L. Meincke, D. Shapiro, et al.
Medicine and Health
Evaluation of large language models on mental health: from knowledge test to illness diagnosis
Y. Xu, Z. Fang, et al.
Computer Science
Evaluation of large language models on mental health: from knowledge test to illness diagnosis
Y. Xu, Z. Fang, et al.
