Showing 2026Show all
2 papers · 1 filter
cs.LG2026
LESSER: Post-Training Data Selection with Output-Layer Gradients
Lyuxin David Zhang, Eric Wong, Surbhi Goel +1
The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular approach that ranks training dat…
cs.LG2026
Missingness Bias Calibration in Feature Attribution Explanations
Shailesh Sridhar, Anton Xue, Eric Wong
Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out…