HarDBench demonstrates that current LLMs are highly susceptible to draft-based jailbreak attacks for harmful content in co-authoring scenarios, and a safety-utility balanced alignment via preference optimization significantly reduces such outputs without harming benign performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
HarDBench demonstrates that current LLMs are highly susceptible to draft-based jailbreak attacks for harmful content in co-authoring scenarios, and a safety-utility balanced alignment via preference optimization significantly reduces such outputs without harming benign performance.