ADC: Enhancing Function Calling Via Adversarial Datasets and Code Line-Level Feedback

TL;DR

ADC significantly improves large language models' ability to correctly follow complex function calls by using detailed line-level feedback and adversarial datasets, leading to better robustness and accuracy.

Contribution

This paper introduces ADC, a novel training approach combining process supervision and adversarial data to enhance LLMs' function calling skills.

Findings

Marked improvements on the BFCL benchmark

Enhanced logical reasoning in function calls

Better parameter matching accuracy

Abstract

Large Language Models (LLMs) have made significant strides in Natural Language Processing and coding, yet they struggle with robustness and accuracy in complex function calls. To tackle these challenges, this paper introduces ADC, an innovative approach that enhances LLMs' ability to follow function formats and match complex parameters. ADC utilizes a high-quality code fine-tuning dataset with line-level execution feedback, providing granular process supervision that fosters strong logical reasoning and adherence to function formats. It also employs an adversarial dataset generation process to improve parameter matching. The staged training methodology capitalizes on both enriched code datasets and refined adversarial datasets, leading to marked improvements in function calling capabilities on the Berkeley Function-Calling Leaderboard (BFCL) Benchmark. The innovation of ADC lies in its strategic combination of process supervision, adversarial refinement, and incremental learning, setting a new standard for LLM proficiency in complex function calling.