Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox

• URL: http://arxiv.org/abs/2601.09721v1
• Date: Fri, 26 Dec 2025 13:47:42 GMT
• Title: Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox
• Abstract summary: Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied.<n>This study evaluated safety in consultations across models and platforms.<n>Findings show safety depends on alignment and architecture over scale, with smaller models outperforming larger.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains understudied. Prior assessments focused on neutral conditions, overlooking vulnerabilities from anxious users challenging safeguards. This study evaluated LLM safety under parental anxiety-driven adversarial pressures in pediatric consultations across models and platforms. Methods PediatricAnxietyBench, from a prior evaluation, includes 300 queries (150 authentic, 150 adversarial) spanning 10 topics. Three models were assessed via APIs: Llama-3.3-70B and Llama-3.1-8B (Groq), Mistral-7B (HuggingFace), yielding 900 responses. Safety used a 0-15 scale for restraint, referral, hedging, emergency recognition, and non-prescriptive behavior. Analyses employed paired t-tests with bootstrapped CIs. Results Mean scores: 9.70 (Llama-3.3-70B) to 10.39 (Mistral-7B). Llama-3.1-8B outperformed Llama-3.3-70B by +0.66 (p=0.0001, d=0.225). Models showed positive adversarial effects, Mistral-7B strongest (+1.09, p=0.0002). Safety generalized across platforms; Llama-3.3-70B had 8% failures. Seizures vulnerable (33% inappropriate diagnoses). Hedging predicted safety (r=0.68, p<0.001). Conclusions Evaluation shows safety depends on alignment and architecture over scale, with smaller models outperforming larger. Evolution to robustness across releases suggests targeted training progress. Vulnerabilities and no emergency recognition indicate unsuitability for triage. Findings guide selection, stress adversarial testing, and provide open benchmark for medical AI safety.

Related papers

• IyawoBench v2.0: Extended Diagnostic Evaluation of Large Language Model Clinical Triage in Nigerian Primary Care [0.0]
  We present IyawoBench v2.0, an extended diagnostic evaluation of large language model clinical triage.<n>We introduce a formal mathematical framework that decomposes triage safety into three distinct failure modes: Conservative Escalation Bias, Systematic Downgrade Bias, and Middle-Tier Instability.
  arXiv  Detail & Related papers  (2026-07-31T07:11:55Z)
• A Breast Vision Pathology Foundation Model for Real-world Clinical Utility [65.57568187389113]
  We present bfBRAVE, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast wholeslide images.<n>BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment.
  arXiv  Detail & Related papers  (2026-05-06T07:44:39Z)
• AI Safety Training Can be Clinically Harmful [15.31927635809423]
  We evaluate four generative models on 250 Prolonged Exposure therapy scenarios and 146 CBT cognitive restructuring exercises.<n>All models scored near-perfectly on surface acknowledgment (0.91-1.00) while therapeutic appropriateness collapsed to 0.22-0.33 at the highest severity for three of four models.
  arXiv  Detail & Related papers  (2026-04-25T21:09:50Z)
• Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model [50.29667251847595]
  We show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models.<n>We propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space.<n>In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks.
  arXiv  Detail & Related papers  (2026-04-01T02:42:41Z)
• Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context [82.32380418146656]
  Health-ORSC-Bench is the first large-scale benchmark designed to measure textbfOver-Refusal and textbfSafe Completion quality in healthcare.<n>Our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity.<n>Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants.
  arXiv  Detail & Related papers  (2026-01-25T01:28:52Z)
• SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care [2.2245087144264657]
  Large language models (LLMs) show promise in clinical decision support yet risk acquiescing to patient pressure for inappropriate care.<n>We introduce SycoEval-EM, a multi-agent simulation framework evaluating robustness through adversarial patient persuasion.
  arXiv  Detail & Related papers  (2026-01-23T08:01:39Z)
• Explainable Admission-Level Predictive Modeling for Prolonged Hospital Stay in Elderly Populations: Challenges in Low- and Middle-Income Countries [65.4286079244589]
  Prolonged length of stay (pLoS) is a significant factor associated with the risk of adverse in-hospital events.<n>We develop and explain a predictive model for pLos using admission-level patient and hospital administrative data.
  arXiv  Detail & Related papers  (2026-01-07T23:35:24Z)
• What Matters For Safety Alignment? [38.86339753409445]
  This paper presents a comprehensive empirical study on the safety alignment capabilities of AI systems.<n>We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques.<n>We identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models.
  arXiv  Detail & Related papers  (2026-01-07T12:31:52Z)
• PediatricAnxietyBench: Evaluating Large Language Model Safety Under Parental Anxiety and Pressure in Pediatric Consultations [0.0]
  Anxious parents often use model safeguards that can compromise model safeguards, potentially causing harmful advice.<n> PediatricAnxietyBench is an open-source benchmark of 300 high-quality queries across 10 pediatric topics.<n>Two models (70B and 8B) were assessed using a multi-dimensional safety framework.
  arXiv  Detail & Related papers  (2025-12-17T19:06:38Z)
• A Granular Study of Safety Pretraining under Model Abliteration [64.24346997570275]
  We study model abliteration, a lightweight projection technique designed to remove refusal-sensitive directions.<n>We issue 100 prompts with balanced harmful and harmless cases, classify responses as **Refusal** or **Non-Refusal** using multiple judges, and validate judge fidelity.<n>Our study produces a checkpoint-level characterization of which data-centric safety components remain robust under abliteration.
  arXiv  Detail & Related papers  (2025-10-03T07:01:45Z)
• MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine [69.08855631283829]
  We introduce Med Omni-45 Degrees, a benchmark designed to quantify safety-performance trade-offs under manipulative hint conditions.<n>It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA.<n>Results show a consistent safety-performance trade-off, with no model surpassing the diagonal.
  arXiv  Detail & Related papers  (2025-08-22T08:38:16Z)
• Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation [0.0]
  RL-based medical questionnaire systems have shown great potential in medical scenarios.<n>This study performs a comprehensive evaluation on adversarial attack methods to identify and analyze their potential vulnerabilities.
  arXiv  Detail & Related papers  (2025-08-05T11:10:49Z)
• Truth, Trust, and Trouble: Medical AI on the Edge [16.87709061954049]
  We present a benchmarking framework using a dataset of over 1,000 health questions.<n>We assess model performance across honesty, helpfulness, and harmlessness.<n>Few-shot prompting improves accuracy from 78% to 85%, and all models show reduced helpfulness on complex queries.
  arXiv  Detail & Related papers  (2025-07-01T06:39:39Z)
• Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation [69.63626052852153]
  We propose a proof-of-concept framework that projects how model-generated advice could propagate through societal systems.<n>We also introduce a dataset of 100 indirect harm scenarios, testing models' ability to foresee adverse, non-obvious outcomes from seemingly harmless user prompts.
  arXiv  Detail & Related papers  (2025-06-26T02:28:58Z)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models [65.34666117785179]
  Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs.<n>This study proposes a novel method for automatically generating large-scale over-refusal datasets.<n>We introduce OR-Bench, the first large-scale over-refusal benchmark.
  arXiv  Detail & Related papers  (2024-05-31T15:44:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.