arxiv:2506.05346
Lei Hsiung
hsiung
AI & ML interests
Trustworthy ML
Recent Activity
upvoted a paper 2 days ago
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization liked a dataset 13 days ago
harborframework/parity-experiments authored a paper 3 months ago
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning DatasetsOrganizations
models 11
hsiung/gemma2-9b-alpaca_high_sim_5k
Updated
hsiung/gemma2-9b-alpaca_low_sim_5k
Updated
hsiung/samsum_high_sim_5k
Text Generation • 7B • Updated
hsiung/samsum_low_sim_5k
Text Generation • 7B • Updated
hsiung/pure_bad_low_sim_5k
Text Generation • 7B • Updated
hsiung/pure_bad_high_sim_5k
Text Generation • 7B • Updated
hsiung/list_high_sim_5k
Text Generation • 7B • Updated
hsiung/list_low_sim_5k
Text Generation • 7B • Updated
hsiung/alpaca_low_sim_5k
Text Generation • 7B • Updated • 2
hsiung/alpaca_high_sim_5k
Text Generation • 7B • Updated