14 papers
DOG-DPO:Dynamic Optimization in Geometry for Safety Alignment
Yi Nian, Tiankai Yang, Yudi Zhang +7
Safety alignment for large language models relies on preference data, but current pipelines often train on large, redundant datasets. Existing data selection methods typically scor…
Cat-DPO: Category-Adaptive Safety Alignment
Tiankai Yang, Yi Nian, Xinyuan Li +6
Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most prefere…
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy
Ruiyao Xu, Mihir Parmar, Tiankai Yang +3
Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated preference data remains expen…
No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents
Tiankai Yang, Jiate Li, Yi Nian +5
LLM-based agents increasingly operate across repeated sessions, maintaining task states to ensure continuity. In many deployments, a single agent serves multiple users within a tea…
M3OOD: Automatic Selection of Multimodal OOD Detectors
Yuehan Qin, Li Li, Defu Cao +3
Out-of-distribution (OOD) robustness is a critical challenge for modern machine learning systems, particularly as they increasingly operate in multimodal settings involving inputs…
AD-LLM: Benchmarking Large Language Models for Anomaly Detection
Tiankai Yang, Yi Nian, Shawn Li +9
Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. Within natural lang…