Keynote: Teaching LLMs New Knowledge
Talkat Cassandra Summit 2023 · on Wednesday, 2023-12-13· at 13:30· Grand Ballroom BC (Concourse Exhibit Level)·
summary
Lamini demonstrates concrete ways to inject new domain knowledge into open LLMs: fine-tuning and pretraining combined with prompting and RAG, plus tooling that enforces guaranteed JSON outputs for reliable production parsing. The stack claims to ingest and teach from millions of training points without manual data transformation and offers scaling support—announcing hundreds of compute nodes becoming available—to run adaptation workflows. Emphasis is on measurable behavior change, corrected hallucinations, and shipping models that actually understand business-specific facts.
AI-written summary · about
related talks
05mKeynote: Teaching LLMs New Knowledge
12mKeynote: How LLMs Have Changed the Way Organizations Do AI
40mKeynote
33mOpening Keynote: LLMs, between fantasy and reality - the poin...
28mA community based open source LLM and what it can do for your business
52mGive Your LLMs a Left Brain
42mKeynote: Foundation to Build LLMs
08mKeynote: Plug in and Scale: Serving LLM Models on Kubernetes Ma...