The study examines how the design of audit questions influences perceived bias in large language models (LLMs). Using 40,726 requests across five models and three domains—hiring, lending, and medical triage—the authors find that demographic bias effects are not replicated when the audit is standardized. Instead, the audit’s construction, such as question phrasing and ordering, has a stronger impact on model responses than applicant demographics.
arXiv:2607. 28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender.
The study evaluates ten bias audit instruments across ten advanced language models on occupational gender, age, and socioeconomic status. While each tool reliably detects bias, their rankings of model performance are essentially random, indicating that different audits measure distinct constructs. The findings show that a single audit can identify bias direction within its own framework, but no audit can consistently rank models against one another.
The paper examines whether removing declared language fields from de‑identified résumés eliminates demographic leakage in large language models. By keeping language attributes identical and varying only unstructured prose across five ethnocultural groups and three cue‑salience levels, the authors find that non‑language text still allows target‑group recovery (average 0.757, reaching 1.000 under high salience). They also show that evaluation design—such as allowing or forbidding ties—dramatically affects LLM‑as‑a‑judge outcomes, underscoring the importance of evaluation protocol in bias audits.
arXiv:2506. 23033v5 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment.
PopResume is a population‑representative resume dataset designed for causal fairness auditing of large language model (LLM) and vision‑language model (VLM) resume screeners. It grounds fairness evaluation in real population statistics and preserves natural attribute relationships, enabling path‑specific effect (PSE) analysis that separates business‑necessity from redlining pathways. Using PopResume, the authors evaluated eight models on 60.8K resumes across five occupations and uncovered five discrimination patterns that aggregate metrics missed, demonstrating the value of causally‑grounded auditing.
arXiv:2606. 16723v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is still measured by grading answers.
arXiv:2608. 14399v1 Announce Type: cross Abstract: Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermediate one person's choice among other people and thereby decide, silently and at scale, which physicians become visible.
Large language models (LLMs) are entering decisions in triage and lending, where task-relevant inference must be distinguished from impermissible proxy use. Current audits ask whether decisions change...
The paper audits vision‑language models (CLIP) for gender bias using 1,500 artworks from the Metropolitan Museum of Art, focusing on zero‑shot logit differences for prompts like "masterpiece," "quality," and "influence." Unadjusted results show no significant gender effect and statistical equivalence across models, but high residual variance suggests that global zero‑shot metrics are largely noise‑dominated and may miss fine‑grained biases. The study underscores the need for multivariate confound control, equivalence testing, and provenance auditing when evaluating AI fairness in cultural heritage data.
arXiv:2608.22887v1 Announce Type: new Abstract: Large language models (LLMs) are entering decisions in triage and lending, where task-relevant inference must be distinguished from impermissible proxy...
The paper introduces FAPE, a four‑stage framework for evaluating the post‑processing fairness intervention ThresholdOptimizer across eight diverse domains, including criminal justice, finance, healthcare, and education. It reports that the intervention reduces disparity in most high‑disparity cases but can worsen fairness when baseline disparities are low, and that a single deployment‑time audit is unreliable without continuous monitoring and baseline‑disparity screening.
arXiv:2604.19984v2 Announce Type: replace-cross Abstract: Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs g...