LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
Paper • 2605.29888 • Published • 34
남세현
gdvstd
·
AI & ML interests
None yet
Recent Activity
updated a dataset 19 days ago
gdvstd/cas4133-assn2-pref-dpo published a dataset 19 days ago
gdvstd/cas4133-assn2-pref-dpoOrganizations
upvoted a paper 7 days ago