Marzyeh Ghassemi
Research
Papers
People
Teaching
ML+Health Seminar 2023
Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models
Chantal Shaib
,
Vinith Menon Suriyakumar
,
Byron C Wallace
,
Marzyeh Ghassemi
2025
Cite
URL
Type
Conference paper
Publication
The Thirty-ninth Annual Conference on Neural Information Processing Systems
Related
When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
Escaping the Mode: Multi-Answer Reinforcement Learning in LMs
Position: Benchmarks Do Not Measure Deployment Readiness in Clinical AI
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
WRING Out The Bias: A Rotation-Based Alternative To Projection Debiasing
Cite
×