Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
A bilingual LLM trained with semantic IDs as vocabulary tokens can recommend items and be steered through natural conversation.
eugeneyan.com · Apr 5, 2026
A bilingual LLM trained with semantic IDs as vocabulary tokens can recommend items and be steered through natural conversation.
Replace random hash IDs with semantic tokens so LLMs can natively understand items and enable conversational recommendations.