Related Experiment Video

Updated: May 26, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Persona Routing Associated With Fewer Safety and Monotonicity Violations in Simulated Emergency Large Language Model

Yuusuke Harada^1,2,3

¹School of Medicine, Chiba University, Chiba, JPN.

|May 25, 2026

Abstract

Objective:

The objective of this study was to evaluate whether persona-routing strategies that combine a LEAN persona with a SAFE persona reduce rule-defined contraindication and sequence safety failures, as well as counterfactual monotonicity violations, while preserving efficiency in simulated emergency clinical reasoning. The study also aimed to determine whether such routing can reduce explicit safety failures and monotonicity violations while keeping resource use close to the lean baseline.

Methods:

Using a single ChatGPT deployment (GPT-5.2 Pro; accessed January 2026; San Francisco, CA: OpenAI), we collected Japanese-language persona outputs for 28 synthetic emergency vignettes (56 scenario-level runs) and eight Base/Worse counterfactual pairs (16 comparisons per strategy). We compared four personas (high/low time pressure × LEAN/SAFE) and three routing strategies that escalated from high-time-pressure LEAN persona (P_HL) to high-time-pressure SAFE persona (P_HS) via red flags, dual-run auditing, and optional arbitration. Outputs were constrained to structured JavaScript Object Notation (JSON) and automatically scored for test suggestions, discharge safety-net specificity (0-5), contraindication/sequence safety violations (severity 0-3), and monotonicity violations. Routing outcomes were evaluated as deterministic offline simulations over stored persona outputs; accordingly, reported call counts are simulated expected large language model (LLM) calls rather than separately logged live controller calls.

Results:

The lean baseline suggested the fewest tests (mean: 1.95) but produced safety violations in 8/56 scenarios (14.3%) and monotonicity violations in 10/16 comparisons (62.5%). SAFE personas had 0/56 safety violations and 0/16 monotonicity violations, but suggested more tests (means: 3.38-4.32). Routing eliminated safety violations and reduced monotonicity violations (ROUTER_R1 2/16; ROUTER_R2_CF 0/16) while keeping test counts near the lean baseline in the main router simulation (means: 2.14-2.21) with modest simulated call overhead (ROUTER_R1 1.21 calls; ROUTER_R2_AUDIT 2.00 calls).

Conclusions:

In this single-model, synthetic evaluation, persona routing was associated with fewer rule-defined safety violations (14.3-0%) and monotonicity violations (62.5% with LEAN prompting vs. 12.5% with ROUTER_R1 and 0% with ROUTER_R2_CF) while preserving low test-suggestion counts.

Keywords:

clinical decision support large language model metamorphic testing monotonicity persona prompting routing safety triage

Related Concept Videos

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...

Constraints and Statical Determinacy

Constraints and Statical Determinacy

In structural engineering, the equilibrium of a system is not only determined by its equations of equilibrium but also with the help of constraints. Constraints refer to restrictions on the motion of a system. The proper combinations of constraints can minimize the total number of constraints needed to maintain a system in mechanical equilibrium. When this happens, the system is said to be statically determinate. For such systems, the unknown reaction supports can be estimated using equilibrium...

Types of Errors: Detection and Minimization

Types of Errors: Detection and Minimization

Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...

Reasoning

Reasoning

Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...

Rationalizing Substitutions

Rationalizing Substitutions

Integrals involving non-rational functions are often difficult to evaluate using standard techniques, especially when radicals appear in the integrand. Rationalizing substitution provides a systematic method for simplifying such integrals by converting them into rational forms that are easier to handle.Consider a rod whose linear mass density depends on a constant linear density, a characteristic length, and the distance from the left end of the rod. Determining the total mass requires...

Routh-Hurwitz Criterion II

Routh-Hurwitz Criterion II

In the application of the Routh-Hurwitz criterion, two specific scenarios can arise that complicate stability analysis.
The first scenario occurs when a singular zero appears in the first column of the Routh table. This situation creates a division by zero issues. To resolve this, a small positive or negative number, denoted as epsilon (∈), is substituted for the zero. The stability analysis proceeds by assuming a sign for ∈. If ∈ is positive, any sign change in the first column of the Routh...

Articles linked to this work by shared authors, journal, and citation graph.

Association Between Eyes-Open One-Leg Standing Time and Previous-Year Fall History Among Employees Aged 50-65 Years: A Cross-Sectional Study.

Journal of frailty, sarcopenia and falls·2026

Robustness of a Large Language Model (LLM)-Based Virtual Patient for Japanese History-Taking Training Under Direct and Indirect Instructional Contamination.

Cureus·2026

Prompt-Induced Output Variability and Structured-Output Integrity in Local Open Large Language Models: A Multi-model In Silico Benchmark Using Synthetic Acute-Care Scenarios.

Cureus·2026

A Clinical Quality-Assurance Panel for Patient-Facing Black-Box Large Language Models in Healthcare: Anchored Forced-Choice Drift Monitoring for Sensitive Communication.

Cureus·2026

Association of Self-Selected Hydrogen-Rich Water Consumption with 6-Month Changes in Chair-Stand Performance and Gait Speed among Community-Dwelling Older Adults Attending Community Salons.

Journal of frailty, sarcopenia and falls·2026

Detecting Citation Veneer in Guideline-Grounded Clinical and Public Health Large Language Model (LLM) Outputs: A Clinical Evidence Audit Grid Using CENHOV Tags.

Cureus·2026

See all related articles