Kim, E., Han, S., & Chang, B. (2026). HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing.
Chicago Style (17th ed.) CitationKim, Euntae, Soomin Han, and Buru Chang. HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing. 2026.
MLA (9th ed.) CitationKim, Euntae, et al. HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing. 2026.
Warning: These citations may not always be 100% accurate.