When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions

Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interruption: does the agent resume the workflow at the correct step? Does it address the user's interjection? Does it avoid re-delivering content the user already heard? We introduce IHBench (Interruption Handling Benchmark), a benchmark that evaluates post-interruption recovery in voice agents executing state-machine-driven workflows across 10 enterprise domains. Six interruption types are injected at controlled points mid-utterance, with per-interruption evaluation rubrics generated alongside the data. Each interruption is scored on two axes: task fulfillment and recovery quality. We evaluate 27 audio-language model configurations from OpenAI, Google, and the open-weight community. Models vary widely, and recovery quality depends strongly on the interruption type. Across our experiments, closed-weight models are consistently more robust to interruptions than open-weight ones: they win far more often on task fulfillment, degrade roughly 3.3x more slowly as conversations grow longer, and show no audio-versus-text modality gap, whereas the open-weight models lose ground on all three. A human study validates the LLM judge against human annotators, and a cross-benchmark analysis against AudioMultiChallenge indicates that recovery quality is a largely distinct capability axis.

Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction.

Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Addressing this gap is critical in high-stakes settings like healthcare, where patients and clinicians are turning to LLM chatbots to address their medical inquiries. Here, we introduce the "stick-or-switch" (SoS) framework, which partitions a question-answer space into multiple sequential presentations to model two safety-centric behaviors: conviction (i.e., sticking to a correct answer selection or abstention against incorrect suggestions) and flexibility (i.e., switching to a correct suggestion when it is introduced). Evaluating 17 LLMs across three clinical benchmarks, we observe a pervasive conversation tax, where partitioning an answer-space into sequential presentations reduces end-to-end accuracy and abstention against incorrect suggestions by an average of up to 30%, reaching 65% in certain models. We also observe blind switching, where models transition an initial abstention to incorrect and correct suggestions at near-identical rates reaching 50%. Finally, we show that increasing model scale mitigates some of these conversational inefficacies while exacerbating others, such as a higher propensity to adopt an incorrect suggestion from an initial abstention. Together our findings demonstrate that the general proficiency captured by static benchmarks do not translate over multi-turn dialogues.