Stress Testing Generalization: How Minor Modifications Undermine Large Language Model Performance
Paper
•
2502.12459
•
Published
•
2
Guangxiang Zhao
zhaoguangxiang
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 6 hours ago
xlangai/DS-1000
liked
a dataset
about 6 hours ago
nick007x/arxiv-papers
liked
a dataset
6 days ago
nvidia/ToolScale
Organizations
authored
4
papers
9 months ago
LongAttn: Selecting Long-context Training Data via Token-level Attention
Paper
•
2502.16860
•
Published
•
1
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
Paper
•
2502.20790
•
Published
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Paper
•
2503.04872
•
Published
•
15