AI RESEARCH
From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation at Industry Scale
arXiv CS.AI
•
ArXi:2602.20558v2 Announce Type: replace Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user interaction logs into effective natural language inputs. Existing methods rely on rigid templates that simply concatenate fields, yielding suboptimal representations for recommendation. We propose a data-centric framework that learns verbalization for LLM-based recommendation.