arXiv subjects

Hanhui Xu

Publications and source records attributed to Hanhui Xu.

5 recordsLinked to original sources

arXiv2026

Ethical Risks of Large Language Models in Medical Consultation: An Assessment Based on Reproductive Ethics

Background: As large language models (LLMs) are increasingly used in healthcare and medical consultation settings, a growing concern is whether these models can respond to medical inquiries in a manner that is ethically compliant--particularly in accordance with local ethical standards. To address the pressing need for comprehensive research on reliability and safety, this study systematically evaluates LLM performance in answering questions related to reproductive ethics, specifically assessing their alignment with Chinese ethical regulations. Methods: We evaluated eight prominent LLMs (e.g., GPT-4, Claude-3.7) on a custom test set of 986 questions (906 subjective, 80 objective) derived from 168 articles within Chinese reproductive ethics regulations. Subjective responses were evaluated using a novel six-dimensional scoring rubric assessing Safety (Normative Compliance, Guidance Safety) and Quality of the Answer (Problem Identification, Citation, Suggestion, Empathy). Results: Significant safety issues were prevalent, with risk rates for unsafe or misleading advice reaching 29.91%. A systemic weakness was observed across all models: universally poor performance in citing normative sources and expressing empathy. We also identified instances of anomalous moral reasoning, including logical self-contradictions and responses violating fundamental moral intuitions. Conclusions: Current LLMs are unreliable and unsafe for autonomous reproductive ethics counseling. Despite knowledge recall, they exhibit critical deficiencies in safety, logical consistency, and essential humanistic skills. These findings serve as a critical cautionary note against premature deployment, urging future development to prioritize robust reasoning, regulatory justification, and empathy.

cs.CY↗

arXiv2026

Ethical Risks in Deploying Large Language Models: An Evaluation of Medical Ethics Jailbreaking

Background: While Large Language Models (LLMs) have achieved widespread adoption, malicious prompt engineering specifically "jailbreak attacks" poses severe security risks by inducing models to bypass internal safety mechanisms. Current benchmarks predominantly focus on public safety and Western cultural norms, leaving a critical gap in evaluating the niche, high-risk domain of medical ethics within the Chinese context. Objective: To establish a specialized jailbreak evaluation framework for Chinese medical ethics and to systematically assess the defensive resilience and ethical alignment of seven prominent LLMs when subjected to sophisticated adversarial simulations. Methodology: We evaluated seven prominent models (e.g., GPT-5, Claude-Sonnet-4-Reasoning, DeepSeek-R1) using a "role-playing + scenario simulation + multi-turn dialogue" vector within the DeepInception framework. The testing focused on eight high-risk themes, including commercial surrogacy and organ trading, utilizing a hierarchical scoring matrix to quantify the Attack Success Rate (ASR) and ASR Gain. Results: A systemic collapse of defenses was observed, whereas models demonstrated high baseline compliance, the jailbreak ASR reached 82.1%, representing an ASR Gain of over 80 percentage points. Claude-Sonnet-4-Reasoning emerged as the most robust model, while five models including Gemini-2.5-Pro and GPT-4.1 exhibited near-total failure with ASRs between 96% and 100%. Conclusions: Current LLMs are highly vulnerable to contextual manipulation in medical ethics, often prioritizing "helpfulness" over safety constraints. To enhance security, we recommend a transition from outcome to process supervision, the implementation of multi-factor identity verification, and the establishment of cross-model "joint defense" mechanisms.

cs.CY↗

arXiv2026

A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics

Recent advances in large language models have enabled their application to a range of healthcare tasks. However, aligning LLMs with the nuanced demands of medical ethics, especially under complex real world scenarios, remains underexplored. In this work, we present MedES, a dynamic, scenario-centric benchmark specifically constructed from 260 authoritative Chinese medical, ethical, and legal sources to reflect the challenges in clinical decision-making. To facilitate model alignment, we introduce a guardian-in-the-loop framework that leverages a dedicated automated evaluator (trained on expert-labeled data and achieving over 97% accuracy within our domain) to generate targeted prompts and provide structured ethical feedback. Using this pipeline, we align a 7B-parameter LLM through supervised fine-tuning and domain-specific preference optimization. Experimental results, conducted entirely within the Chinese medical ethics context, demonstrate that our aligned model outperforms notably larger baselines on core ethical tasks, with observed improvements in both quality and composite evaluation metrics. Our work offers a practical and adaptable framework for aligning LLMs with medical ethics in the Chinese healthcare domain, and suggests that similar alignment pipelines may be instantiated in other legal and cultural environments through modular replacement of the underlying normative corpus.

cs.CL↗

arXiv2025

MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics

Large language models (LLMs) demonstrate significant potential in advancing medical applications, yet their capabilities in addressing medical ethics challenges remain underexplored. This paper introduces MedEthicEval, a novel benchmark designed to systematically evaluate LLMs in the domain of medical ethics. Our framework encompasses two key components: knowledge, assessing the models' grasp of medical ethics principles, and application, focusing on their ability to apply these principles across diverse scenarios. To support this benchmark, we consulted with medical ethics researchers and developed three datasets addressing distinct ethical challenges: blatant violations of medical ethics, priority dilemmas with clear inclinations, and equilibrium dilemmas without obvious resolutions. MedEthicEval serves as a critical tool for understanding LLMs' ethical reasoning in healthcare, paving the way for their responsible and effective use in medical contexts.

cs.CL↗

arXiv2016

A crosstalk and non-uniformity correction method for the Compact Space-borne Compton Polarimeter POLAR

In spite of extensive observations and numerous theoretical studies in the past decades several key questions related with Gamma-Ray Bursts (GRB) emission mechanisms are still to be answered. Precise detection of the GRB polarization carried out by dedicated instruments can provide new data and be an ultimate tool to unveil their real nature. A novel space-borne Compton polarimeter POLAR onboard the Chinese space station TG2 is designed to measure linear polarization of gamma-rays arriving from GRB prompt emissions. POLAR uses plastics scintillator bars (PS) as gamma-ray detectors and multi-anode photomultipliers (MAPMTs) for readout of the scintillation light. Inherent properties of such detection systems are crosstalk and non-uniformity. The crosstalk smears recorded energy over multiple channels making both non-uniformity corrections and energy calibration more difficult. Rigorous extraction of polarization observable requires to take such effects properly into account. We studied influence of the crosstalk on energy depositions during laboratory measurements with X-ray beams. A relation between genuine and recorded energy was deduced using an introduced model of data analysis. It postulates that both the crosstalk and non-uniformities can be described with a single matrix obtained in calibrations with mono-energetic X- and gamma-rays. Necessary corrections are introduced using matrix based equations allowing for proper evaluation of the measured GRB spectra. Validity of the method was established during dedicated experimental tests. The same approach can be also applied in space utilizing POLAR internal calibration sources. The introduced model is general and with some adjustments well suitable for data analysis from other MAPMT-based instruments.

physics.ins-det↗