Qingwei Lin
2 papers · Latest:
Cryptography & Security
CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
CI-Work introduces a benchmark to evaluate enterprise LLM agents' ability to handle sensitive information, revealing high privacy violation rates and a utility-privacy trade-off.
2604.21308
Information RetrievalDUET: Joint Exploration of User Item Profiles in Recommendation System
Duet is a novel LLM-based recommendation system that jointly generates user and item textual profiles, outperforming baselines by aligning them for better recommendations.
2604.13801
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.