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.

Adaptive interfaces are a promising attempt to overcome contemporary problems due to the increasing complexity of human-computer interaction. They are designed to tailor a system's interactive behavior with consideration of individual needs of human users and altering conditions within an application environment. For building adaptive user interfaces, we developed a system that interacts with users in a variety of terminals. The system has three categories. First we have MPEG-4 Binary Format for Scenes(BIFS) [5,6] for creating interactive media. The second category is the adaptor chain which brings about a user interface depending upon user preferences, terminal capabilities and network constraints. The third category is the iPlayer or Interactive Player that plays the transferred media data and interacts with the user. The player, when implemented finally, operates on Win32, WinCE and Linux and plays MPEG-4 video and MP3 audio.