DBScholar

Back to papers

LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System

Summary: LEADRE uses intent-aware prompts and multifaceted LLM knowledge to generate diverse ads, with auxiliary tasks and DPO aligning models to advertising objectives. Latency-aware hybrid serving scales the system to tens of billions of daily requests and improves online GMV. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
14271
Venue
VLDB
Year
2025
Pagerank
-
Overall Rank
13,326 | 8.58%
DOI
10.14778/3750601.3750602

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{li_vldb25,
        title = {{LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System}},
        author = {Li, Fengxin and Li, Yi and Liu, Yue and Zhou, Chao and Wang, Yuan and Deng, Xiaoxiang and Xue, Wei and Liu, Dapeng and Xiao, Lei and Gu, Haijie and Jiang, Jie and Liu, Hongyan and Qin, Biao and He, Jun},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {4763--4776},
        doi = {10.14778/3750601.3750602},
        url = {https://doi.org/10.14778/3750601.3750602},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Semantically Similar Papers