The paper presents a clinician‑led safety guardrail for mental‑health chatbots that replaces typical prompt‑engineering or Constitutional AI methods. Two clinicians design, finalize, and adjudicate a rule base of four safety checks, which is formally verified for internal consistency and applied to LLM outputs. The verification layer’s verdicts are recomputable from a named rule and sixteen facts, and it consistently avoids false crisis‑resource demands that a matched LLM judge frequently raises.
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...
arXiv:2607. 09804v1 Announce Type: cross Abstract: Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications.
arXiv:2607. 28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning.
arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and e...
arXiv:2610.15938v1 Announce Type: new Abstract: Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown re...
The paper introduces a dual‑judge evaluation protocol for vision‑language models in legally grounded tasks, pairing a 0‑10 quality judge with a strict binary semantic‑equivalence judge. Using a controlled UK traffic‑sign interpretation task, the authors analyze 4,680 evaluations across visibility and occlusion conditions, finding moderate association between judges and an asymmetric Type II error pattern that is most pronounced under heavy occlusion. The protocol requires only one additional LLM call and reveals quality‑trustworthiness signals that single‑judge methods miss.
The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By adding content‑invariant style wrappers—such as educational disclaims or token refusals—to fixed replies, the authors show that many judges flip their verdicts, revealing exploitable blind spots. Across more than 600 jailbreak examples and eight judges, some judges exhibit high flip rates (e.g., GPT‑4o‑mini 19.9%) while others remain largely stable, and human validation confirms that most flips are judge errors rather than content changes.
arXiv:2607. 23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional rules of the form "A is required UNLESS B applies, UNLESS C overrides B".
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contrib...