Xiaoyang Gu

Zhentao Xu, Shangjing Zhang, Emir Poyraz et al.

Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system, which extracts implicit and explicit signals from noisy longitudinal behavioral data, stores them in a structured form, and supports low-latency retrieval. Building industrial-grade long-term memory for LLM agents raises five challenges: scalability, low-latency retrieval, privacy constraints, cross-domain generalizability, and observability. We introduce the Hierarchical Long-Term Semantic Memory (HLTM) framework, which organizes textual data into a schema-aligned memory tree that captures semantic knowledge at multiple levels of granularity, enabling scalable ingestion, privacy-aware storage, low-latency retrieval, and transparent provenance; HLTM further incorporates an adaptation mechanism to generalize across diverse use cases. Extensive evaluations on LinkedIn's Hiring Assistant show that HLTM improves answer correctness and retrieval F1 significantly by more than 10%, while significantly advancing the Pareto frontier between query and indexing latency. HLTM has been deployed in LinkedIn's Hiring Assistant to power core personalization features in production hiring workflows.

Ling Hu, Yuemei Xu, Xiaoyang Gu et al.

Despite the impressive performance of large language models (LLMs), they can present unintended biases and harmful behaviors driven by encoded values, emphasizing the urgent need to understand the value mechanisms behind them. However, current research primarily evaluates these values through external responses with a focus on AI safety, lacking interpretability and failing to assess social values in real-world contexts. In this paper, we propose a novel framework called ValueExploration, which aims to explore the behavior-driven mechanisms of National Social Values within LLMs at the neuron level. As a case study, we focus on Chinese Social Values and first construct C-voice, a large-scale bilingual benchmark for identifying and evaluating Chinese Social Values in LLMs. By leveraging C-voice, we then identify and locate the neurons responsible for encoding these values according to activation difference. Finally, by deactivating these neurons, we analyze shifts in model behavior, uncovering the internal mechanism by which values influence LLM decision-making. Extensive experiments on four representative LLMs validate the efficacy of our framework. The benchmark and code will be available.

Xie Lu, Xiaoguang Wang, Xiaoyang Gu

In August 2019, we introduced to our members and customers the idea of moving LinkedIn's two core talent products -- Jobs and Recruiter -- onto a single platform to help talent professionals be even more productive. This single platform is called the New Recruiter & Jobs. A critical and difficult part of this effort is migrating their existing data from the legacy database to the new database and ensure there is no data discrepancy and no down time. In this article, we will discuss the general architecture for a successful data migration and the thought process we followed. Then we expand these ideas to our circumstances and explain in more detail about our specific challenges and solutions. In the Ramp Process section, we explain the inherent difficulties in satisfying our success criteria and describe how we overcome these difficulties and fulfill the success criteria practically.