HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing

Documenti analoghi

• NOAH: Benchmarking Narrative Prior driven Hallucination and Omission in Video Large Language Models
  di: Lee, Kyuho, et al.
  Pubblicazione: (2025)
• SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script
  di: Kim, Eunwon, et al.
  Pubblicazione: (2024)
• Alignment Data Map for Efficient Preference Data Selection and Diagnosis
  di: Lee, Seohyeong, et al.
  Pubblicazione: (2025)
• CoAuthorAI: A Human in the Loop System For Scientific Book Writing
  di: Tian, Yangjie, et al.
  Pubblicazione: (2026)
• Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
  di: Dong, Yiting, et al.
  Pubblicazione: (2024)