Automated Tailoring of Large Language Models for Industry-Specific Downstream Tasks
Shreya Saxena, Siva Prasad, I Muneeswaran, Advaith Shankar, V Varun, Saisubramaniam Gopalakrishnan, Vishal Vaddina · 2024
Foundational Large Language Models (LLMs) are pre-trained generally on huge corpora encompassing broad subjects to become versatile and generalize to future downstream tasks. However, their effectiveness falls short when dealing with tasks that are highly specialized to a specific use case. Even when adopting current prompt engineering techniques like few-shot or Chain-of-Thought reasoning prompts, the required level of results is not yet achievable directly with foundational models alone. The alternative approach is to fine-tune the LLM, but a common challenge is the limited availability of task-specific training data. In this talk, we will introduce an end-to-end automated framework to tailor a model to specific downstream tasks for an industry where the first step is to generate task-specific custom data from unstructured documents. Next, we will discuss our optimized distributed training pipeline for fine-tuning LLMs on the generated data. Finally, we will provide an overview of the statistical metrics and customized metrics we employ for assessing the performance of the fine-tuned LLM. This automated framework alleviates the burden of manual adjustments and streamlines the process to provide a model that is fully customized to suit the unique requirements of any specific business use case.