High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning framework to create unified, interpretable, and concise textual user representations from heterogeneous sources, improving personalization in large-scale job platforms while ensuring scalability and latency efficiency.

Contribution

The paper presents a novel RL-based method for synthesizing unified user representations from diverse textual data, incorporating implicit signals and rule-based constraints for improved personalization.

Findings

Significant improvements in downstream business metrics on LinkedIn.

Effective, scalable, labeling-free user representation construction.

Compatibility with LLM-based systems for personalization.

Abstract

Effective personalization on large-scale job platforms requires modeling members based on heterogeneous textual sources, including profiles, professional data, and search activity logs. As recommender systems increasingly adopt Large Language Models (LLMs), creating unified, interpretable, and concise representations from heterogeneous sources becomes critical, especially for latency-sensitive online environments. In this work, we propose a novel Reinforcement Learning (RL) framework to synthesize a unified textual representation for each member. Our approach leverages implicit user engagement signals (e.g., clicks, applies) as the primary reward to distill salient information. Additionally, the framework is complemented by rule-based rewards that enforce formatting and length constraints. Extensive offline experiments across multiple LinkedIn products, one of the world's largest job platforms, demonstrate significant improvements in key downstream business metrics. This work provides a practical, labeling-free, and scalable solution for constructing interpretable user representations that are directly compatible with LLM-based systems.