Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction
cs.IR, cs.AI, cs.CL, cs.LG
Submitted: 2026-10-11
Updated: 2026-10-11
Sources
- Deploying Semantic ID-based Generative Retrieval for Large-Scale Podcast Discovery at Spotify
- DeepSeek-V3 Technical Report
- OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
- PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
- Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations
- Cut Your Losses in Large-Vocabulary Language Models
- Constrained Auto-Regressive Decoding Constrains Generative Retrieval
- Qwen3 Technical Report
- Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation
- Instruction-Following Evaluation for Large Language Models
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
- MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition