CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nasarian, Elham, Neog, Abhilash, Tsui, Kwok-Leung, HosseiniChimeh, Niyousha
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911633400397824
author Nasarian, Elham
Neog, Abhilash
Tsui, Kwok-Leung
HosseiniChimeh, Niyousha
author_facet Nasarian, Elham
Neog, Abhilash
Tsui, Kwok-Leung
HosseiniChimeh, Niyousha
contents Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information. However, ensuring clinical safety and factual reliability remains a critical challenge. In practice, AI-generated responses may be conditionally correct yet medically inappropriate, as models often fail to interpret patient context and tend to produce agreeable responses rather than challenge unsafe assumptions. Unlike clinicians, who infer risk from incomplete information, LLMs frequently lack contextual awareness. Moreover, real-world patient interactions are open-ended and underspecified, unlike structured benchmark settings. We present CareGuardAI, a risk-aware safety framework for patient-facing medical question answering that addresses two key failure modes: clinical safety risk and hallucination risk. The framework introduces Clinical Safety Risk Assessment (SRA), inspired by ISO 14971, and Hallucination Risk Assessment (HRA) to evaluate medical risk and factual reliability. At inference time, CareGuardAI employs a multi-stage pipeline consisting of a controller agent, safety-constrained generation, and dual risk evaluation, followed by iterative refinement when necessary. Responses are released only when both SRA and HRA are less than or equal to 2, ensuring clinically acceptable outputs with bounded latency. We evaluate CareGuardAI on PatientSafeBench, MedSafetyBench, and MedHallu, covering both safety and hallucination detection. Across these benchmarks, the framework consistently outperforms strong baseline models, including GPT-4o-mini, demonstrating the importance of context-aware, risk-based, inference-time safety mechanisms for reliable deployment in healthcare.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26959
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs
Nasarian, Elham
Neog, Abhilash
Tsui, Kwok-Leung
HosseiniChimeh, Niyousha
Computers and Society
Artificial Intelligence
Multiagent Systems
Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information. However, ensuring clinical safety and factual reliability remains a critical challenge. In practice, AI-generated responses may be conditionally correct yet medically inappropriate, as models often fail to interpret patient context and tend to produce agreeable responses rather than challenge unsafe assumptions. Unlike clinicians, who infer risk from incomplete information, LLMs frequently lack contextual awareness. Moreover, real-world patient interactions are open-ended and underspecified, unlike structured benchmark settings. We present CareGuardAI, a risk-aware safety framework for patient-facing medical question answering that addresses two key failure modes: clinical safety risk and hallucination risk. The framework introduces Clinical Safety Risk Assessment (SRA), inspired by ISO 14971, and Hallucination Risk Assessment (HRA) to evaluate medical risk and factual reliability. At inference time, CareGuardAI employs a multi-stage pipeline consisting of a controller agent, safety-constrained generation, and dual risk evaluation, followed by iterative refinement when necessary. Responses are released only when both SRA and HRA are less than or equal to 2, ensuring clinically acceptable outputs with bounded latency. We evaluate CareGuardAI on PatientSafeBench, MedSafetyBench, and MedHallu, covering both safety and hallucination detection. Across these benchmarks, the framework consistently outperforms strong baseline models, including GPT-4o-mini, demonstrating the importance of context-aware, risk-based, inference-time safety mechanisms for reliable deployment in healthcare.
title CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs
topic Computers and Society
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2604.26959