Medical Ethics and Value Alignment
Research on aligning LLMs with medical ethics, human values in healthcare contexts, and ethical decision-making frameworks
Medical Ethics and Value Alignment
Research on Large Language Models in Medical Ethics and Value Alignment
ValueCompass: Measuring Human-AI Value Alignment
A framework for evaluating how well AI systems reflect diverse human values
Measuring AI & Human Values
A New Framework for Value Alignment in LLMs
Confidence-Based LLM Routing
Enhancing AI reliability through self-assessment mechanisms
AI Safety Blindspots in Scientific Labs
Evaluating LLMs for Laboratory Safety Knowledge
AI-Powered Ethics Review for Research
Using specialized LLMs to streamline IRB processes
Balancing Ethics and Utility in LLMs
A new framework that enhances safety without compromising functionality
Enhancing Safety in Visual AI
Addressing Critical Gaps in Vision-Language Model Safety
Fairness in AI-Powered X-Ray Diagnostics
Evaluating bias in CLIP-based models for medical imaging
AI-Assisted Moral Analysis in Vaccination Debates
Using LLMs to support human annotators in identifying moral framing on social media
The Ethics of Search Engine Power
A novel framework for evaluating search engines beyond algorithms
Open Foundation Models: Transforming Healthcare
Exploring the potential of non-proprietary LLMs for personalized medicine
Fair-MoE: Enhancing Fairness in Medical AI
A novel approach to tackle bias in Vision-Language Models
Rethinking AI Regulation in Healthcare
A global framework for governing generative AI and LLMs in medicine
Bias in AI-Driven Palliative Care
How LLMs like GPT-4o perpetuate inequities in healthcare
Building Trustworthy AI Systems
Navigating Safety, Bias, and Privacy Challenges in Modern AI
The Confidence Gap in LLMs
Measuring and addressing overconfidence in large language models
Catastrophic Risks in AI Decision-Making
Analyzing CBRN Threats from Autonomous LLM Agents
Relationship Blueprints for Human-AI Cooperation
How social roles and norms should guide AI design and interaction
Protecting Young Minds in the AI Era
Evaluating and Enhancing LLM Safety for Children
Beyond One-Size-Fits-All: Pluralistic AI in Healthcare
Introducing VITAL: A benchmark for diverse values alignment in medical AI
What Makes AI Seem Conscious?
Quantifying the features that shape human perception of AI consciousness
Trust & Intent: LLMs in Healthcare
Multinational analysis of DeepSeek adoption factors
Ethical Design of AI Personalities
Creating responsible LLM-based conversational agents
Evaluating Medical Ethics in AI
A Framework for Testing LLMs in Healthcare Ethics
Transforming Healthcare with LLMs
A framework for responsible AI integration in clinical settings
Reducing Hallucination Risk in Critical Domains
A framework for setting hallucination standards in domain-specific LLMs
Hallucinations: Bridging Human and AI Cognition
What machine 'hallucinations' teach us about human cognition
Uncovering Hidden Biases in LLMs
A framework for detecting subtle, nuanced biases in AI systems
Predicting Human Choices from Text Descriptions
First large-scale study of decision-making with textually described risks
Addressing Bias in Medical AI Systems
Evaluating and mitigating demographic biases in retrieval-augmented medical QA
Can We Trust LLMs in High-Stakes Environments?
Enhancing reliability through uncertainty quantification
The Double-Edged Sword of Humanized AI
How LLM chatbots mirror humans and risk manipulation
Trust Through Transparency in AI
Combining LLMs with Rule-Based Systems for Trustworthy AI
AI-Powered Consent Form Generation
Enhancing clinical research compliance with AI assistance
Breaking Free From LLM Chat Search Constraints
How functional fixedness limits users' interactions with AI systems
Bridging the Gap: AI Models in Critical Domains
A framework for deploying large AI models in healthcare, education, and legal settings
Hidden Biases in Healthcare AI
Systematic Review Reveals Bias Patterns in Clinical LLMs
Fair AI in Medical Decision-Making
Evaluating LLM fairness in organ allocation using voting theory
The Ethics vs. Performance Trade-Off in AI
Measuring the cost of respecting web crawling opt-outs in LLM training
LExT: Towards Evaluating Trustworthiness of Natural Language...
By Krithi Shailya, Shreya Rajpal...
Building Fair AI Systems
Developing comprehensive fairness standards for the 6G era
Uncovering Bias in Language Models
Using Metamorphic Testing to Identify Fairness Issues in LLaMA and GPT
Credibility Detection with LLMs
Using AI to identify trustworthy visual content
