3 papers
cs.CL2026
No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation
Dimitri Staufer, David Hartmann, Ibrahim Baroud
Person names are widely used as prompt variables in LLM evaluations of factuality, privacy leakage, bias and abstention, but when a name's evidential status is uncontrolled, measur…
cs.HC2026
Human-Centred LLM Privacy Audits: Findings and Frictions
Dimitri Staufer, Kirsten Morehouse, David Hartmann +1
Large language models (LLMs) learn statistical associations from massive training corpora and user interactions, and deployed systems can surface or infer information about individ…
cs.HC2025
Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations
David Hartmann, Amin Oueslati, Dimitri Staufer +3
Commercial content moderation APIs are marketed as scalable solutions to combat online hate speech. However, the reliance on these APIs risks both silencing legitimate speech, call…