Qingyun Wu

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

2025 · arXiv (Cornell University)

We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Real-world security analysts must sift through a large number …

Factorization Bandits for Interactive Recommendation

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

We perform online interactive recommendation via a factorization-based bandit algorithm. Low-rank matrix completion is performed over an incrementally constructed user-item preference matrix, where an upper confidence bound based item selection strategy is developed to balance …

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

2020

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. …