arXiv (All)
open access
When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression
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 model declined a harmful request under the servi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Dataset Watermarking with Provable Black-Box Detection#1130546
- Misalignment of Low-Loss Regions Causes Grokking#1155555
- Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation#1083091
- Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization#924212
- Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization#919981
Record · ID 1115634
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive