Benign fine-tuning of foundation models induces large, heterogeneous, and often contradictory changes in safety metrics across general and domain-specific benchmarks.
In- creased llm vulnerabilities from fine-tuning and quantiza- tion.arXiv preprint arXiv:2404.04392
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ZipMoE delivers up to 72.77% lower inference latency and 6.76x higher throughput for on-device MoE models via lossless compression and cache-affinity scheduling with a claimed provable guarantee.
citing papers explorer
-
Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains
Benign fine-tuning of foundation models induces large, heterogeneous, and often contradictory changes in safety metrics across general and domain-specific benchmarks.
-
ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling
ZipMoE delivers up to 72.77% lower inference latency and 6.76x higher throughput for on-device MoE models via lossless compression and cache-affinity scheduling with a claimed provable guarantee.