6 papers
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Yihui Wang, Yonghui Yang, Jilong Liu +3
Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen ma…
Controllable Value Alignment in Large Language Models through Neuron-Level Editing
Yonghui Yang, Yihui Wang, Junwei Li +6
Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands. However, existing steeri…
CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment
Jilong Liu, Yonghui Yang, Pengyang Shao +5
Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect sup…
Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
Yonghui Yang, Wenjian Tao, Jilong Liu +6
Safety alignment of large language models remains brittle under domain shift and noisy preference supervision. Most existing robust alignment methods focus on uncertainty in alignm…
InterMind: Doctor-Patient-Family Interactive Depression Assessment Empowered by Large Language Models
Zhiyuan Zhou, Jilong Liu, Sanwang Wang +3
Depression poses significant challenges to patients and healthcare organizations, necessitating efficient assessment methods. Existing paradigms typically focus on a patient-doctor…
Debate over Mixed-knowledge: A Robust Multi-Agent Reasoning Framework for Incomplete Knowledge Graph Question Answering
Jilong Liu, Pengyang Shao, Wei Qin +3
Knowledge Graph Question Answering (KGQA) aims to improve factual accuracy by leveraging structured knowledge. However, real-world Knowledge Graphs (KGs) are often incomplete, lead…