conftrace_

parameter removal

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

hessian-based pruning (1) embedding dimension reduction (1) transformer compression (1) harmful queries (1) harmless helpful honest (1) safety realignment (1) fine-tuned language model (1) model sparsification (1) inference speedup (1) post-training compression (1)

Papers

OptiPrune: Effective Pruning Approach for Every Target Sparsity COLING 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 SliceGPT: Compress Large Language Models by Deleting Rows and Columns ICLR 2024