← back to paper

Review history

arxiv: 2507.18631 · 2 revisions

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   122276 ms 26315 in 13340 out 2026-08-15T18:09:08.414796+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   128533 ms 26330 in 13775 out 2026-08-06T14:32:09.128467+00:00