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

arXiv: https://arxiv.org/abs/2608.29241 · HTML: https://mlsanity.com/paper/2608.29241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Full-Duplex-Bench v1.5: Evaluating Overlap Handling for Full-Duplex Speech Models](https://mlsanity.com/paper/2507.23159/) (2025)
- [Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics](https://mlsanity.com/paper/2503.01174/) (2025)
- [Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner](https://mlsanity.com/paper/2510.07838/) (2025)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions](https://mlsanity.com/paper/2505.17818/) (2025)
- [EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents](https://mlsanity.com/paper/2605.13841/) (2026)
- [Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge](https://mlsanity.com/paper/2604.21406/) (2026)
- [EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions](https://mlsanity.com/paper/2604.16456/) (2026)
- [IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows](https://mlsanity.com/paper/2606.19595/) (2026)
- [ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems](https://mlsanity.com/paper/2501.08208/) (2025)
- [Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial](https://mlsanity.com/paper/2603.05413/) (2026)
- [Evaluating Speech-to-Text x LLM x Text-to-Speech Combinations for AI Interview Systems](https://mlsanity.com/paper/2507.16835/) (2025)
- [WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue](https://mlsanity.com/paper/2511.16544/) (2025)

## Abstract (arXiv)

Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a cascaded architecture (speech-to-text -> LLM -> text-to-speech), so when a patient cuts the agent off mid-utterance, clinically required content can be lost even when the model handles cooperative transcripts well. Yet clinical conversational-AI benchmarks almost universally assume patients wait for the agent to finish, missing interruption-induced loss of required content. We present a transcript-based evaluation of interruption recovery, adapting conversation-analytic overlap categories into three operational types (recognitional, competitive, transitional sub-unit) and testing four deployment-oriented, non-reasoning LLM configurations across four cells spanning history-taking (information gathering) and FAQ (information provision), scored on whether the agent preserves the clinically required content. In the gathering cells, target-question failure varied across models; in the provision cells, where arms are directly comparable, failure rose for every model. Rankings differ across cells, and competitive FAQ interruption produced 30/30 provision-coverage failures for all four models (Wilson 95% CI: 88.6-100.0%; baseline 0/30 for three, 4/30 for Llama). A brief apology marker ("sorry to interrupt") shifts recovery by tens of percentage points, inconsistently across models, and for one it reduces recovery. Interruption robustness therefore cannot be a single score: evaluation must be content-grounded, reported per cell, and matched to the deployment's interruption profile.