arxiv
PublishedMay 8, 2026 at 4:00 AM
—neutral
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
Publisher summary· verbatim
arXiv:2605.06327v1 Announce Type: cross Abstract: Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context divergence as an ob
Models mentioned
02Related
05- arxiv8dA Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
- arxiv14dGraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval
- arxiv14dDrugRAG: Enhancing Pharmacy LLM Performance Through A Novel Retrieval-Augmented Generation Pipeline
- arxiv20dKrause Synchronization Transformers
- arxiv21dA Large Language Model Based Pipeline for Review of Systems Entity Recognition from Clinical Notes
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
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning13harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning13harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models13harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents13hThe Bubble Brief
WEEKLYRead safety insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗