Xuanli He
2 papers · Latest:
Natural Language Processing
Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
A new streaming probing method for LLMs uses segment-level coherence to robustly detect harmful intent, especially in CBRN, reducing false alarms.
2604.14865
Software EngineeringStarCoder 2 and The Stack v2: The Next Generation
StarCoder2 is a next-generation open-source Code LLM trained on a vastly expanded and diverse dataset, achieving state-of-the-art performance on multiple code benchmarks while being more parameter-efficient than larger models.
2402.19173
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.