Open-source foundational language models unlock a new opportunity for building AI inside law firms. This paper provides a practical approach on how law firms can leverage the latest advancements in LLMs and Generative AI without compromising on data privacy and security through open-source models for internal use cases.
The paper explores how these models can be fine-tuned and present a novel addition of intelligence engineering to the traditional knowledge management process that involves instruction fine-tuning language models to infinitely scale access to explicit knowledge. Including a practical demonstration of this technical approach with a proof of concept using an open-source foundational model based on the GPT-3 architecture and an open-source dataset of contracts.
Source: CEUR Workshop Proceedings
Leave a Reply