arxiv
PublishedJune 10, 2026 at 4:00 AM
—neutral
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
Publisher summary· verbatim
arXiv:2606.09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact. In this study, we explore alignmen
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivMODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning4harxivPosition: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!4harxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions4harxivThe Impossibility of Eliciting Latent Knowledge4hThe Bubble Brief
WEEKLYRead quantization insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗