Sai Kolasani
Researcher at UC Berkeley’s RISE Lab (and Arize AI Intern)
Best podcasts with Sai Kolasani
Ranked by the Snipd community
6 snips
Jun 28, 2024 • 44min
RAFT: Adapting Language Model to Domain Specific RAG
Sai Kolasani, a researcher at UC Berkeley’s RISE Lab and Arize AI Intern, discusses RAFT, a method to adapt language models for domain-specific question-answering. RAFT improves models' reasoning by training them to ignore distractor documents, enhancing performance in specialized domains like PubMed and HotpotQA. The podcast explores RAFT's chain-of-thought-style response, data curation, and optimizing performance in domain-specific tasks.
