Papers with turn-level accuracy
Transfer Learning for Generalizable Automated LLM Improvement Pipeline for IVR Navigation (2026.acl-industry)
Copied to clipboard
| Challenge: | Using a human-labeled ground truth dataset, we can transfer specialized prompts from one task to another, reducing the complexity of the task. |
| Approach: | They propose a production-quality automated LLM pipeline which leverages a small number of human-labeled ground truth datasets to transfer specialized prompts from one task to another. |
| Outcome: | The proposed model reduces prompt complexity by up to 80% and obtains 82% turn-level accuracy in real-world industrial healthcare settings, surpassing a human-designed prompt at 79%. |