4 papers
The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning
Rahul Nair, Chun Tao
Deploying Small Language Models (SLMs) on edge devices requires efficient fine-tuning strategies that adapt models to new tasks without degrading their general capabilities. In thi…
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
Rahul Nair, Bhanu Tokas, Hannah Kerner
When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias am…
DPA: A one-stop metric to measure bias amplification in classification datasets
Bhanu Tokas, Rahul Nair, Hannah Kerner
Most ML datasets today contain biases. When we train models on these datasets, they often not only learn these biases but can worsen them -- a phenomenon known as bias amplificatio…
Classification Drives Geographic Bias in Street Scene Segmentation
Rahul Nair, Gabriel Tseng, Esther Rolf +2
Previous studies showed that image datasets lacking geographic diversity can lead to biased performance in models trained on them. While earlier work studied general-purpose image…