arXiv cs.CL
· Papers
Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
arXiv:2607.20436v1 Announce Type: new Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption. A checkpoint can appear fixed under evaluation-style prompts while the same behavior persists under ordinary-use prompts. Ou