AI Safety Evals - Paper Reading Club

This week we have our second author presentation in a row! Hongye Cao will present his research SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks, a step beyond most safety benchmarks, which focus on single jailbreak attacks in single-turn dialogs. ​Every week, someone will present for up to 20 minutes followed by 40 minutes of discussion. RSVP to join, sign up to present, or contact us at evalsreadinggroup@gmail.com with questions. Everyone is welcome!