Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
3
Pruning LLMs can amplify biases, but Debias-SparseGPT shows that you can reduce these biases while maintaining performance, even under aggressive sparsity constraints.
Instruction tuning boosts model confidence but often at the cost of rationale diversity and calibration accuracy.
Fairness degradation in language models can silently escalate before performance metrics signal any issues, revealing a hidden danger in synthetic data training.