3 papers
cs.CL2026
LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
Jingyue Cong, Estrid He, Zhuang Li +5
Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local risks, overlooking failures wh…
cs.CL2026
Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models
Jingyue Cong, Andy Song, Yang Yu +7
Machine unlearning for large language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit…
cs.AI2026
Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds
Waqas Khan, Tabinda Sarwar, Jingyue Cong +2
Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes reques…