BLUE aligns LLM-generated textual user profiles with embedding-based recommendation objectives via reinforcement learning and next-item text supervision, yielding better zero-shot performance and cross-domain transfer than baselines.
Embedding-Frozen Sequential Recommendation with Qwen3-1.7B.Table 14 shows thatBLUE remains consistently strong when built on top ofQwen3-1.7B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bridging Textual Profiles and Latent User Embeddings for Personalization
BLUE aligns LLM-generated textual user profiles with embedding-based recommendation objectives via reinforcement learning and next-item text supervision, yielding better zero-shot performance and cross-domain transfer than baselines.