# ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making

arXiv: https://arxiv.org/abs/2608.09024 · HTML: https://mlsanity.com/paper/2608.09024/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [MedDialog: Two Large-scale Medical Dialogue Datasets](https://mlsanity.com/paper/2004.03329/) (2020)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents](https://mlsanity.com/paper/2501.14654/) (2025)
- [NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes](https://mlsanity.com/paper/2310.15959/) (2023)
- [A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets](https://mlsanity.com/paper/2204.08997/) (2022)
- [MedGemma 1.5 Technical Report](https://mlsanity.com/paper/2604.05081/) (2026)
- [PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions](https://mlsanity.com/paper/2505.17818/) (2025)
- [Benchmarking emergency department triage prediction models with machine learning and large public electronic health records](https://mlsanity.com/paper/2111.11017/) (2021)
- [MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations](https://mlsanity.com/paper/2410.14204/) (2024)
- [ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues](https://mlsanity.com/paper/2109.00430/) (2021)
- [Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning](https://mlsanity.com/paper/2502.07143/) (2025)
- [3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark](https://mlsanity.com/paper/2504.13861/) (2025)
- [Synthetic Patient-Physician Dialogue Generation from Clinical Notes Using LLM](https://mlsanity.com/paper/2408.06285/) (2024)
- [AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data](https://mlsanity.com/paper/2506.04032/) (2025)
- [MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis](https://mlsanity.com/paper/2606.03416/) (2026)
- [TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records](https://mlsanity.com/paper/2603.10035/) (2026)
- [Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines](https://mlsanity.com/paper/2601.03627/) (2026)
- [Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes](https://mlsanity.com/paper/2601.21551/) (2026)

## Abstract (arXiv)

Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prioritize limited clinical resources. At presentation, however, information may be limited to a chief complaint and initial vital signs. Clinically important details, including symptom onset and progression, associated symptoms, medical history, and medication use, are often obtained through focused conversation. Effective triage therefore requires clinicians to identify information gaps, ask appropriate follow-up questions, and update their assessment as new evidence becomes available. Most existing ED benchmarks evaluate acuity prediction from a fixed clinical snapshot. Although this formulation measures predictive performance after patient information has been assembled, it does not capture the interactive process through which triage-relevant evidence is elicited and interpreted. Existing medical dialogue datasets support the study of clinical communication, but dialogue statements are not always linked to temporally ordered events in the electronic health record (EHR). We introduce EHR2Dial-Triage, an agentic conversation-generation framework and benchmark grounded in MIMIC-IV-ED. The framework constructs triage conversations under explicit role-based and temporal information boundaries. Each accepted patient disclosure is linked to its supporting EHR event and the first dialogue turn at which it becomes available. EHR2Dial-Triage enables controlled evaluation of information elicitation, evidence use, five-level Emergency Severity Index prediction, and patient-facing communication across models and patient personas. It provides a structured setting for studying conversational triage as a dynamic process of clinical information acquisition, reasoning, and communication.