2025 "test-time intervention" Papers
2 papers found
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
Yisong Xiao, Aishan Liu, Siyuan Liang et al.
NeurIPS 2025posterarXiv:2510.01243
2
citations
Neural Causal Graph for Interpretable and Intervenable Classification
Jiawei Wang, Shaofei Lu, Da Cao et al.
ICLR 2025poster
1
citations