6 citations · 7 across the 7 of their papers we have counts for
4 papers · 1 filter
Whose Effect Is It? How Objectives Inflate Learned Subspace Interventions
Toygar Tanyel, Serkan Ayvaz
Interpretability often locates concepts by copying part of a language model's state from one input into another (activation patching). A larger output change counts as stronger evi…
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…
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…
Developing Linguistic Patterns to Mitigate Inherent Human Bias in Offensive Language Detection
Toygar Tanyel, Besher Alkurdi, Serkan Ayvaz
With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred,…