English

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation

Information Retrieval 2026-05-01 v1 Artificial Intelligence

Abstract

Large language model (LLM)-based generative list-wise recommendation has advanced rapidly, but decoding remains sequential and thus latency-prone. To accelerate inference without changing the target distribution, speculative decoding (SD) uses a small draft model to propose several next tokens at once and a target LLM to verify and accept the longest prefix, skipping multiple steps per round. In generative recommendation, however, each item is represented by multiple semantic-ID tokens, often with separators, and current drafts typically treat these tokens uniformly. This overlooks two practical facts: (i) a token's semantics depend on its within-item slot, and (ii) uncertainty tends to increase with speculation depth. Without modeling these effects, SD's speedups can be limited. We introduce PAD-Rec, Position-Aware Drafting for generative Recommendation, a lightweight module that augments the draft model with two complementary signals. Item position embeddings explicitly encode the within-item slot of each token, strengthening structural awareness. Step position embeddings encode the draft step, allowing the model to adapt to depth-dependent uncertainty and improve proposal quality. To harmonize these signals with base features, we add simple gates: a learnable coefficient for item slots and a context-driven gate for draft steps. The module is trainable, easy to integrate with standard draft models, and adds negligible inference overhead. Extensive experiments on four real-world datasets show up to 3.1x wall-clock speedup and about 5% average wall-clock speedup gain over strong SD baselines, while largely preserving recommendation quality.

Keywords

Cite

@article{arxiv.2604.27747,
  title  = {Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation},
  author = {Jiaju Chen and Chongming Gao and Chenxiao Fan and Haoyan Liu and Qingpeng Cai and Peng Jiang and Xiangnan He},
  journal= {arXiv preprint arXiv:2604.27747},
  year   = {2026}
}
R2 v1 2026-07-01T12:43:25.369Z