The paper reports that counterfactual fairness audits of clinical language‑model agents are unreliable without accounting for a per‑action instability floor. By repeatedly running identical vignettes, the authors found that actions changed 8.7% of the time, with instability varying eightfold across actions. A second model confirmed a pooled floor of 6.7%, showing that any reported fairness estimate lacking this floor cannot be interpreted as evidence of disparity.
arXiv:2609.03221v3 Announce Type: replace-cross Abstract: Counterfactual fairness audits of clinical language-model agents report a flip rate: how often an action changes when only the patient's demo...
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:2607. 28608v1 Announce Type: new Abstract: Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups.
arXiv:2604. 17359v2 Announce Type: replace-cross Abstract: Language models asked to simulate psychiatric patients produce cases that survive inspection one at a time and populations that match no real one.
The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.
The paper proposes a scalable, automated method for auditing candidate‑job matching systems for demographic bias. It employs large‑language‑model agents to generate neutral resumes, injects controlled demographic variations, ranks candidates with a fine‑tuned embedding model, and evaluates nine fairness metrics across counterfactual, group‑fairness, and merit‑aware families, producing a composite risk report. Experiments on a small corpus show that single‑score audits miss nuanced issues, underscoring the need for multi‑metric evaluation and LLM‑generated audits as a low‑cost complement to human reviews.
The paper introduces a new evaluation method called "same-input rerun" to assess the consistency of clinical language‑model agents across repeated runs. By replaying 1,000 MedAgentBench tasks with identical inputs, the authors find that action‑level outputs—such as test orders, medication requests, and referrals—vary significantly, even when benchmark scores remain unchanged. The study demonstrates that current benchmarks, which typically evaluate only a single run per task, can miss substantial behavioral divergence.
arXiv:2608.31017v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 1...
arXiv:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.
arXiv:2604. 07709v4 Announce Type: replace-cross Abstract: A heavily safety-trained model will hand a physician the full, patient-followable benzodiazepine taper and refuse it to the patient who needs it, over identical clinical facts; the knowledge is present either way.
arXiv:2607. 18828v1 Announce Type: new Abstract: Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks.
arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the n...