Summary of Adaptable and Precise: Enterprise-scenario Llm Function-calling Capability Training Pipeline, by Guancheng Zeng et al.
Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline
by Guancheng Zeng, Wentao Ding, Beining Xu, Chi Zhang, Wenqiang Han, Gang Li, Jingjing Mo, Pengxu Qiu, Xinran Tao, Wang Tao, Haowen Hu
First submitted to arxiv on: 20 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a training pipeline for designing scenario-specific agent applications by leveraging enterprises’ API assets. The pipeline consists of data synthesis, augmentation, model fine-tuning, and performance evaluation. The authors generated 1,260 AI-generated samples and 1,035 manually-labeled samples in the digital HR agent scenario using the Qwen2.5-Coder-7B-Instruct model as the base model and fine-tuned it with the LoRA method on four GPUs. The results show that the fine-tuned model outperforms GPT-4 and GPT-4o in accuracy on the test set, demonstrating the effectiveness of the proposed pipeline. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps companies create special AI assistants by using their existing computer programs (APIs). They need these assistants to help with specific tasks, like HR work. The authors created a plan for training these assistants, which involves making data, fine-tuning models, and testing them. They used this plan to make 1,260 AI-made examples and 1,035 labeled examples in the HR scenario. Their results show that their trained model is better than other models at getting the right answers. |
Keywords
» Artificial intelligence » Fine tuning » Gpt » Lora
