Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits
Siddharth Vohra, Manikandan Ravikiran
Whether a language model looks demographically biased can depend on how the audit asks its question. A charitable-aid benchmark reports that the same models favor minority applican…
cs.CL2026
When Models Defer to Wrong Answers: A Robustness Audit of Source-Attributed Cues in Multiple-Choice QA
Manikandan Ravikiran, Siddharth Vohra
Language models often receive a question together with a claim about what another source answered. We audit whether such claims destabilize answers in multiple-choice question answ…