A blank image removes 61% of correct answers, yet on GMAI-MMBench no trained probe is less confident on answers unchanged by image replacement, and a question-only classifier recovers much of adaptation's ranking gain but certifies far less.
Mohammad M. Ghassemi, Kundan Thind, Mohammad M. Ghassemi· 3 citations
INCONVENIENT is introduced, a benchmark designed to study robustness to convenience-sample bias and provides explicit control over both the direction and severity of relationship shifts, enabling a systematic assessment of robustness to convenience sampling.
Sara Rezaeimanesh, C. Klochko, Kundan Thind et al.· 0 citations
This work studies model-internal confidence readouts under white-box, image-only attacks constrained to preserve the generated answer byte-identically, showing that comparable confidence movement can be induced at the representation level rather than only through adversarial images.
Reza Khanmohammadi, Ivan Brugere, Simerjot Kaur et al.· arXiv.org· 0 citations
This work evaluates seven confidence estimators, three inference-only and four trained internal probes, across five open-weight LVLMs and four conditions from three financial visual question-answering benchmarks, one bilingual; every probe is trained only on natural images and applied to finance without adaptation, so...
Mohammad M. Ghassemi, Simerjot Kaur, Charese H. Smiley et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.