arXiv:2610.32943v1 Announce Type: cross Abstract: Generative recommendation with semantic IDs represents each item as a sequence of discrete codes derived from its semantic representation and predict...
REGER is a unified framework that enhances generative recommendation by explicitly modeling inter-item relations through semantic pretraining, history encoding, and SID generation. It pretrains the model to generate semantic neighbors’ IDs, uses combined global and local attention to capture historical context, and introduces a hierarchical preference decomposition over the SID prefix tree. The approach also distills a discriminative teacher’s full conditional distributions to improve next-token predictions, yielding consistent performance gains on real-world datasets.
DecisionRank introduces an on-policy distillation (OPD) method that trains decision models to replicate a generative LLM’s ranking knowledge by converting the student’s document scores into a ranked sequence and using a teacher to provide conditional feedback. The approach combines item‑space OPD with offline ranking supervision, achieving state‑of‑the‑art results on retrieval benchmarks such as TREC DL, BEIR, and BRIGHT. Even with a 1.7B parameter model, DecisionRank outperforms its 27B generative teacher on TREC DL19–23, and at 8B it surpasses the generative listwise counterpart while running 24.5× faster on TREC DL and 16.7× faster on BRIGHT.
REGER is a framework that enhances generative recommendation by explicitly modeling inter-item relations through semantic pretraining, refined history encoding, and SID generation. It pretrains the model to generate semantic neighbors’ IDs, uses a combination of global and local attention to capture context, and introduces a hierarchical preference decomposition that allows exact factorization of collaborative preferences. The method also distills a discriminative teacher’s full conditional distributions to improve next-token predictions, yielding consistent performance gains on real-world datasets.
arXiv:2603. 23183v2 Announce Type: replace-cross Abstract: Recent advances in generative recommendation have leveraged pretrained LLMs by formulating sequential recommendation as autoregressive generation over a unified token space comprising language tokens and itemic identifiers, where each item is represented by a compact sequence of discrete tokens, namely Semantic IDs (SIDs).
The paper introduces Common‑Support Distillation (CSD), a logits‑based framework for transferring knowledge across different tokenizers by constructing a shared support between teacher and student distributions. CSD handles both one‑to‑one alignments using explicit common‑token pairs and other alignments by creating a virtual support via the autoregressive chain rule, while a residual event ensures normalization. Experiments on Llama‑3.2‑1B, Gemma3‑1B‑PT, Qwen, and Phi models show that CSD consistently outperforms existing cross‑tokenizer methods, achieving up to 1.8‑point gains over the best alternative and surpassing both continued pretraining and same‑tokenizer distillation.
arXiv:2510. 21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history.
The paper introduces API, a framework that adapts pretrained interpretable features for generative recommendation. By reusing sparse autoencoder‑derived feature indices as a reusable semantic ID vocabulary, API avoids additional vocabulary learning and preserves item distinctions even with limited token budgets. The Semantic Prediction Adapter learns user preferences from interaction histories, combining feature‑index and strength predictions to score candidates, while also providing explainable retrieval through feature contributions linked to pretrained semantic annotations.
arXiv:2608. 10929v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the behavioral anchors that align item spaces, such as overlapping users and shared interaction signals, are often sparse, unavailable, or privacy-sensitive across clients.
arXiv:2607. 25209v1 Announce Type: cross Abstract: Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization.
arXiv:2609.22227v1 Announce Type: cross Abstract: Generative retrieval represents each item by a short Semantic ID and casts recommendation as autoregressive generation of that sequence. Because the...
The paper introduces GR4AD‑X, an enhanced generative recommendation framework for large‑scale advertising that tackles three key limitations of its predecessor: unreliable deterministic SID assignment, limited scalability of backbone models, and weak credit assignment in sequence‑level value optimization. GR4AD‑X improves SID reliability via Multi‑Path assignment, expands model capacity across complementary dimensions for better efficiency, and aligns generation with commercial value through Unified Value‑Guided Generation and Discrimination (UniVGD), which optimizes prefix‑level rewards, prunes beams, and reranks discriminatively. Online A/B tests on Kuaishou’s advertising platform show a 3.07% revenue increase over the baseline while meeting strict latency and throughput constraints.