@inproceedings{wang-etal-2025-decoding-latent,
    title = "Decoding in Latent Spaces for Efficient Inference in {LLM}-based Recommendation",
    author = "Wang, Chengbing  and
      Zhang, Yang  and
      Wang, Zhicheng  and
      Shi, Tianhao  and
      Bao, Keqin  and
      Feng, Fuli  and
      Chua, Tat-Seng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.401/",
    doi = "10.18653/v1/2025.findings-emnlp.401",
    pages = "7591--7603",
    ISBN = "979-8-89176-335-7",
    abstract = "Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores bypassing language-space decoding by directly matching candidate items with the LLM{'}s internal thought representations in the latent space, eliminating the time-consuming autoregressive process to reduce computational costs. Towards this, we introduce Light Latent-space Decoding ($L2D$), an effective and efficient latent-space decoding method. $L2D$ represents user-preferred items by using the hidden states of test sequences reflecting the LLM{'}s internal thought, and obtains candidate item representations from the hidden states of training sequences labeled with the corresponding candidate items. It then matches the two types of representations to decode items, achieving latent-space decoding. In this way, it enables efficient decoding without altering the LLM{'}s generative tuning paradigm, thereby preserving performance. Extensive empirical results demonstrate that $L2D$ is more than 10x faster than language-space decoding while maintaining or enhancing performance."
}