Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports
Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
Language-model self-reports are evidence about behavior in a prompt environment, not by themselves evidence of a self-model. We investigate counterfactual reports about affect-like…
cs.CL2026
Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz
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 un…