Graph-enhanced Large Language Models in Asynchronous Plan Reasoning: A Talk with Fangru Lin, DPhil NLP @University of Oxford
Join us for an enlightening session on "Graph-enhanced Large Language Models in Asynchronous Plan Reasoning" with Fangru Lin, a DPhil NLP student from the University of Oxford and a Clarendon scholar. This talk is part of the Computer Vision Talks series and will take place on Saturday, 24th August 2024 at 10:00 AM EST. Register here to save your spot.
Fangru Lin will introduce the "Plan Like a Graph (PLaG)" method, which significantly enhances the performance of large language models (LLMs) by breaking down tasks into sub-tasks and arranging them into an execution graph. This approach allows for both parallel and sequential execution of tasks, improving the performance of LLMs without the need for fine-tuning. Learn how this method can be applied to both closed and open-source LLMs, such as GPT-4 and LLaMA-2, achieving state-of-the-art results.
This session is an excellent opportunity for anyone interested in advanced prompt engineering and complex reasoning tasks. Whether you are familiar with the PLaG method or new to it, this talk promises to broaden your understanding and offer practical applications for enhancing LLM performance.
Support the Computer Vision Talks by engaging with our related LinkedIn posts and YouTube channel. Share your thoughts, ask questions, and help amplify the reach and impact of these valuable discussions within the community.