When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression
arXiv:2609.31678v1 Announce Type: new Abstract: KV cache compression is widely used for long context LLM inference under memory constraints, while deployed systems typically score refusals after generation with keyword filters or learned classifiers. Such monitors are intended to indicate whether a…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-30 04:00 · arXiv cs.LG
When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression