Oral ยท Sydney
CURE: Counterfactual Unsafe-token Re-masking for Diffusion Large Language Model Test-time Alignment
Time not published yetRoom not published
- When
- Time not published yet
- Where
- Room not published
- Poster
- Poster of this paper
- Authors
- Lichao Wang, Mingquan Zhang, Xian Zhang, Juntao Dai, Chi Liu, Yaodong Yang, Jingwei Yi
- Organisations
- Beijing Institute of Technology, Peking University, AIG, Beijing Academy of Artificial Intelligence
- QRS classification
- Language models, Generative models, Causal inference