Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing their potential for executing complex tasks crucially relies on enhancements in their function calling capabilities. This paper identifies a critical gap in existing function calling models, where performance varies significantly across benchmarks, often due to being misled by specific naming conventions. To address such an issue, we introduce Hammer, a novel family of foundation models specifically engineered for on-device function calling. Hammer employs an augmented dataset that enhances models' sensitivity to irrelevant functions and incorporates function masking techniques to minimize misleading. Our empirical evaluations reveal that Hammer not only outperforms larger models but also demonstrates robust generalization across diverse benchmarks, achieving sota results. Our open source contributions include a specialized dataset for irrelevance detection, a tuning framework for enhanced generalization, and the Hammer models, establishing a new standard for function calling performance.
@article{arxiv.2410.04587,
title = {Hammer: Robust Function-Calling for On-Device Language Models via Function Masking},
author = {Qiqiang Lin and Muning Wen and Qiuying Peng and Guanyu Nie and Junwei Liao and Jun Wang and Xiaoyun Mo and Jiamu Zhou and Cheng Cheng and Yin Zhao and Jun Wang and Weinan Zhang},
journal= {arXiv preprint arXiv:2410.04587},
year = {2024}
}