Investigating the Effect of Intraclass Variability in Temporal Ensembling Paper • 2008.08956 • Published Aug 21, 2020
Hearsay: Vision-Language Medical Diagnoses Without an Image Paper • 2607.26886 • Published Jul 29
Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines Paper • 2609.04579 • Published Sep 7
The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits Paper • 2609.09048 • Published Sep 8
When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA Paper • 2609.08934 • Published Sep 8