What an amazing time I had at hashtag#AAAI24 in Vancouver! 🏔️☁️

Had the chance to present my latest long paper on the use of retrieval-augmented LLMs for long-form question answering in the legal domain, where we introduced both a unique dataset for the task and experimented with small open-source LLMs in various learning settings.

It was truly an enriching experience to be able to discuss the benefits and limitations of these models in specialized domains with the most brilliant AI minds in the world.

→ Paper: https://ojs.aaai.org/index.php/AAAI/article/view/30232

→ Code: https://github.com/maastrichtlawtech/lleqa

→ Models & Data: https://huggingface.co/datasets/maastrichtlawtech/lleqa