Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models

• URL: http://arxiv.org/abs/2608.24534v1
• Date: Tue, 25 Aug 2026 13:20:03 GMT
• Title: Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models
• Abstract summary: We propose Neurosymbolic Alignment, a training-time framework that couples a 7B clinical LLM with an HGNN-based Physiological World Model.<n> Candidate responses are scored using homeostatic constraints, multi-hop path plausibility, and drug-interaction penalties.<n> Evaluation is performed on the Clinical Safety Benchmark (CSB), a 2,500-scenario benchmark for physiological constraint violations in generative clinical reasoning.
• Score: 34.30791848883716
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. We investigate whether safety alignment can be improved by grounding preference optimization in structured physiological knowledge rather than text-only supervision. Methods: We propose Neurosymbolic Alignment, a training-time framework that couples a 7B clinical LLM with an HGNN-based Physiological World Model over an 847K-node biomedical knowledge graph. Candidate responses are scored using homeostatic constraints, multi-hop path plausibility, and drug-interaction penalties, and the resulting rankings drive iterative on-policy ORPO updates. Evaluation is performed on the Clinical Safety Benchmark (CSB), a 2,500-scenario benchmark for physiological constraint violations in generative clinical reasoning. Results: Relative to ORPO, the proposed method improves CSS from 69.5% to 90.8% (+21.3 pp), reduces physician-evaluated HR from 14.1% to 5.1% on the blinded subset, and improves DID from 72.8% to 91.6%. These gains are corroborated by an HGNN-independent Rule-Engine Safety Score (RSS: 86.4%, +21.2 pp over ORPO; r=0.97 concordance with CSS). The method also exceeds GPT-4 (5-shot) on all safety metrics despite a 10x parameter disadvantage, and outperforms an inference-time self-correction pipeline (SFT+SelfCorrect) by 11.4 pp CSS. Under synthetic EHR-style noise, 84.2% CSS is retained. Ablation analysis shows that HGNN scoring (-16.2 pp) and iterative training (-11.5 pp) are the dominant contributors. PhysioScore calibration against 200 clinician labels yielded ECE = 0.038 and kappa = 0.91. Conclusion: Training-time physiological grounding produces measurable and independently verifiable safety improvements in open-weight clinical LLMs under controlled evaluation. External validation on real clinical data is required to determine whether these gains transfer to deployment settings

Related papers

• Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies [17.85382282659117]
  We compared the performance of large language models (LLMs) and reasoning strategies for automated OvarianAd Reportingal and Data Fable System (ORADS) classification.<n>The feature-based hybrid architecture demonstrated almost the best performance, achieving an accuracy of 99.2% (387 of 390) and agreement with the reference standard.
  arXiv  Detail & Related papers  (2026-08-24T10:04:17Z)
• Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models [0.00304396936267654]
  Large language models can produce confident but protocol-invalid answers in domains where procedural compliance is critical.<n>This paper presents Answer Engineering, a deterministic runtime and authoring layer that applies localized rule-guided interventions to the visible reasoning trajectory.<n>The method is evaluated on a controlled clinical benchmark for sudden sensorineural hearing loss.
  arXiv  Detail & Related papers  (2026-06-19T05:47:44Z)
• 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)
• A Neuro-Symbolic System for Interpretable Multimodal Physiological Signals Integration in Human Fatigue Detection [3.430778683859764]
  We propose a neuro-symbolic architecture that learns four interpretable physiological concepts, oculomotor dynamics, gaze stability, prefrontal hemodynamics, and multimodal, from eye-tracking and neural hemodynamics, functional near-infrared spectroscopy, (fNIRS) windows using attention-based encoders, and combines them with differentiable approximate reasoning rules using learned weights and soft thresholds.<n>We apply this system to fatigue classification from multimodal physiological signals, a domain that requires models that are accurate and interpretable, with internal reasoning that can be inspected for safety-critical use.
  arXiv  Detail & Related papers  (2026-03-25T14:41:02Z)
• PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology [48.732366302949515]
  Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety.<n>We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions.<n>We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration.
  arXiv  Detail & Related papers  (2026-03-02T00:50:39Z)
• Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems [19.880569341968023]
  Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety.<n>We propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics.
  arXiv  Detail & Related papers  (2026-01-21T16:40:41Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Early Prediction of Multi-Label Care Escalation Triggers in the Intensive Care Unit Using Electronic Health Records [1.116791976498254]
  This study proposes a multi-label classification framework to predict Care Escalation Triggers (CETs)<n>CETs are defined using rule-based criteria applied to data from hours 24 to 72.<n>We train and evaluate multiple classification models on a cohort of 85,242 ICU stays.
  arXiv  Detail & Related papers  (2025-09-15T20:40:45Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment [46.776978552161395]
  Small language models (SLMs) offer a cost-effective alternative to large language models such as GPT-4.<n>SLMs offer a cost-effective alternative, but their limited capacity requires biomedical domain adaptation.<n>We propose a novel framework for adapting SLMs into high-performing clinical models.
  arXiv  Detail & Related papers  (2025-05-15T21:40:21Z)

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.