TGViewer
AINL Conference AINL Conference @ainlconf · 490 subscribers
Post #166 943
SafetyBench: Russian-language LLM safety benchmark for toxicity evaluation and jailbreak robustness testing grounded in Russian law

#AINL2026 #NLP
📺 https://www.youtube.com/watch?v=6SvzoQHfd7w
▶️ https://vkvideo.ru/video-38193760_456239047?list=ln-KERAZuWKiz49sZCjNZ
YouTube SafetyBench Russian language LLM safety benchmark for toxicity evaluation and jailbreak robustness Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
  • 🔥 6
Open in Telegram All posts from @ainlconf
More from @ainlconf
  1. Sep 17, 2026Russian Instruction-Aware Text Retrieval: A Synthetic Dataset, Benchmark, and Adaptation —…
  2. Sep 15, 2026A multi-head-based architecture for effective morphological tagging in russian with open d…
  3. Sep 10, 2026StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems — Sergey Volko…
  4. Sep 8, 2026Data Filtering Methods for Training Language Models — Egor Shevchenko; Elena Bruches #AINL…
  5. Sep 3, 2026FILTERING AND DISCOVERING SCIENTIFIC DISCOURSE ON TELEGRAM: A PIPELINE FOR MACHINE LEARNIN…
  6. Sep 1, 2026Four Faces of Homography in Russian: Disambiguating Them All with a Single TTS-Ready Model…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →