EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Large scale retrieval for the LinkedIn feed using causal language models

Sudarshan Srinivasa Ramanujam, Antonio Alonso, Saurabh Kataria, Siddharth Dangi, Akhilesh Gupta, Birjodh Singh Tiwana, Manas Haribhai Somaiya, Luke Simon, David Byrne, Madhu Arun, Sojeong Ha, Sen Zhou und 12 weitere

AI Magazine · 2026-09 · 47 (3)

DOI: 10.1002/aaai.70078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI Magazine, online erschienen am 22.08.2026. Verfasst von Sudarshan Srinivasa Ramanujam und 23 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In large‐scale recommendation systems like LinkedIn's, the retrieval stage is critical for narrowing billions of potential candidates to a manageable subset for ranking. LinkedIn's feed now serves suggested content based on the topical interests of members, where 2000 candidates are retrieved from several million candidates with a latency budget of a few milliseconds and inbound QPS of several thousand per second. This paper presents a novel retrieval approach that fine tunes a large causal language model (Meta's LLaMA 3) as a dual encoder to generate high quality embeddings for both users (members) and content (items), using only textual input. We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine tuning at LinkedIn scale, and infrastructure for low latency, cost effective online serving. We share our findings on how quantizing numerical features in the prompt enables the information getting encoded in the embedding facilitating greater alignment between the retrieval and ranking layer. The system was evaluated using offline metrics and an online A/B test, which showed substantial improvements in member engagement. We observed significant gains among newer members, who often lack strong network connections, indicating that high‐quality suggested content aids retention. This work demonstrates how generative language models can be effectively adapted for real time, high throughput retrieval in industrial applications.

Zitieren

APA

Ramanujam, S. S., Alonso, A., Kataria, S., Dangi, S., Gupta, A., Tiwana, B. S., Somaiya, M. H., Simon, L., Byrne, D., Arun, M., Ha, S., Zhou, S., Akterskii, A., Liu, Z., Sriram, S., Xiong, Z., Pei, Z., Shao, A., Li, A., …, & Firooz, H. (2026). Large scale retrieval for the LinkedIn feed using causal language models. AI Magazine, 47(3). https://doi.org/10.1002/aaai.70078

Vancouver

Ramanujam SS, Alonso A, Kataria S, Dangi S, Gupta A, Tiwana BS, et al. Large scale retrieval for the LinkedIn feed using causal language models. AI Magazine. 2026;47(3). doi:10.1002/aaai.70078

BibTeX
@article{Ramanujam2026,
  author = {Ramanujam, Sudarshan Srinivasa and Alonso, Antonio and Kataria, Saurabh and Dangi, Siddharth and Gupta, Akhilesh and Tiwana, Birjodh Singh and Somaiya, Manas Haribhai and Simon, Luke and Byrne, David and Arun, Madhu and Ha, Sojeong and Zhou, Sen and Akterskii, Andrei and Liu, Zhanglong and Sriram, Samira and Xiong, Zihan and Pei, Zhoutao and Shao, Angela and Li, Alex and Xiao, Annie and Kolb, Caitlin and Kistler, Thomas and Moore, Zach and Firooz, Hamed},
  title = {Large scale retrieval for the LinkedIn feed using causal language models},
  journal = {AI Magazine},
  year = {2026},
  volume = {47},
  number = {3},
  doi = {10.1002/aaai.70078}
}
Kostenlos starten →