Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport
Shaan Shah, Meenakshi Khosla
Standard representational similarity methods align each layer of a network to its best match in another independently, producing asymmetric results, lacking a global alignment scor…
cs.LG2025
Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
Kaustubh Ponkshe, Shaan Shah, Raghav Singhal +1
Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign o…