When Your LLM Systems Meet Real Life: Talks by AI/ML Practitioners
Join us for an engaging in-person meetup in San Francisco featuring talks by LLM and AI practitioners.🌉
This event will delve into the latest advancements and best practices in evaluating LLM-powered applications and we'll explore the often overlooked blind spots in Retrieval-Augmented Generation (RAG) datasets.
Topics that will be covered:
✅ LLM Evaluation: Explore methodologies and metrics for assessing the performance and reliability of your LLM applications.
✅ Biases in RAG: Hidden biases and gaps can compromise the accuracy and reliability of generated responses. We will demonstrate how to identify areas with overrepresentation and underrepresentation, using a case study to highlight these blind spots.
This meetup is sponsored by Deepchecks, Neo4J, & Pinecone.
This meetup is ideal for AI researchers, data scientists, AI application engineers, and technology managers building RAG applications.
Agenda:
5:30 pm: Doors open
6:00 pm: Talks
8:00 pm: Socializing
Talks:
GPT on a Leash: Principles of Systematic LLM Evaluation with Philip Tannor, DeepChecks
From Unseen to Seen: Shedding Light on Overlooked Blindspots in RAG Datasets with Alison Cossette
Location: Alloy Collective, 431 Tehama St., San Francisco, CA