Paper-Conference

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Scaling Sparse Feature Circuit Finding for In-Context Learning
In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?
Rethinking AI Cultural Alignment
Towards Interpreting Visual Information Processing in Vision-Language Models
Best-of-N Jailbreaking
Interpreting Learned Feedback Patterns in Large Language Models
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
Large Language Models Relearn Removed Concepts