pith. sign in

and Michael, Julian and Perez, Ethan and Treutlein, Johannes , title =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

representative citing papers

Self-Mined Hardness for Safety Fine-Tuning

cs.LG · 2026-05-04 · unverdicted · novelty 7.0

Self-mined hardness from model rollouts reduces WildJailbreak attack success rates to 1-3% on Llama models but increases over-refusal on benign prompts, which mixing with adversarially-framed benign prompts partially mitigates.

citing papers explorer

Showing 2 of 2 citing papers.