PPL
Brinnae Bent
Papers (4)
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the promptFeature Visualization Recovers Known Cortical Selectivity from TRIBE v2When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language ModelsWhen Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models