DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
Paper
•
2502.05163
•
Published
•
18
Fan Yin
fanyin3639
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM
Guardrails
updated
a dataset
4 months ago
fanyin3639/safety_bingo_test_w_probs
updated
a dataset
4 months ago
fanyin3639/BingoGuardTrain-wo-severity
Organizations
None yet