Merve Unuvar


2024

pdf bib
Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
Ibrahim Abdelaziz | Kinjal Basu | Mayank Agarwal | Sadhana Kumaravel | Matthew Stallone | Rameswar Panda | Yara Rizk | G P Shrivatsa Bhargav | Maxwell Crouse | Chulaka Gunasekara | Shajith Ikbal | Sachindra Joshi | Hima Karanam | Vineet Kumar | Asim Munawar | Sumit Neelam | Dinesh Raghu | Udit Sharma | Adriana Meza Soria | Dheeraj Sreedhar | Praveen Venkateswaran | Merve Unuvar | David Daniel Cox | Salim Roukos | Luis A. Lastras | Pavan Kapanipathi
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track

An emergent research trend explores the use of Large Language Models (LLMs) as the backbone of agentic systems (e.g., SWE-Bench, Agent-Bench). To fulfill LLMs’ potential as autonomous agents, they must be able to identify, call, and interact with a variety of external tools and application program interfaces (APIs). This capability of LLMs, commonly termed function calling, leads to a myriad of advantages such as access to current and domain-specific information in databases and the outsourcing of tasks that can be reliably performed by tools. In this work, we introduce Granite-20B-FunctionCalling, a model trained using a multi-task training approach on seven fundamental tasks encompassed in function calling. Our comprehensive evaluation on multiple out-of-domain datasets, which compares Granite-20B-FunctionCalling to more than 15 other best proprietary and open models, shows that Granite-20B-FunctionCalling has better generalizability on multiple tasks across seven different evaluation benchmarks. Moreover, Granite-20B-FunctionCalling shows the best performance among all open models and ranks among the top on the Berkeley Function Calling Leaderboard (BFCL).