VirtueMap Profiles LLM Ethical Behavior Using Aristotelian Framework

Ioannis Tzachristas, John Pavlopoulos· June 30, 2026 View original

Key takeaways

  • VirtueMap profiles LLM ethical behavior using an Aristotelian virtue-ethics framework.
  • LLMs are evaluated by ranking responses to non-lethal ethical dilemmas.
  • Human-validated reference orderings define the ground truth for virtue scoring.
  • LLMs show high consistency but notable differences in specific virtues like Courage and Justice.

Who benefits

AI/ML DevelopmentEthics & GovernancePublic PolicyHealthcareBFSI

Summary

This research introduces VirtueMap, a framework that profiles Large Language Models (LLMs) based on Aristotelian virtues like justice and courage by evaluating their responses to ethical dilemmas. It uses human-validated rankings of responses to score LLMs, revealing high consistency across models but also notable differences in specific virtues.

Large Language Models (LLMs) frequently encounter ethical dilemmas where multiple responses are defensible, each reflecting different priorities such as fairness or honesty. This paper presents VirtueMap, a novel framework designed to characterize these ethical patterns through the lens of Aristotelian virtue ethics. VirtueMap asks humans or LLMs to rank five responses to seven non-lethal, non-political ethical dilemmas. Reference orderings for each virtue (Practical Wisdom, Justice, Truthfulness, Courage, Temperance) are established through human consensus. LLM rankings are then scored against these ground truths using normalized Borda alignment, generating a virtue profile. Applying VirtueMap to nine LLM families, the study found high mean rank consistency, indicating stable ethical tendencies. However, significant differences emerged in virtues like Courage, Temperance, and Justice. The research also provides an interactive website for local browser-based profiling, allowing comparison of human and LLM virtue profiles.

Why it matters

For professionals developing or deploying LLMs, VirtueMap provides a structured way to assess and understand the ethical biases and priorities embedded within these models, which is crucial for responsible AI development and deployment in sensitive contexts.

How to implement this in your domain

  1. 1Utilize VirtueMap or similar frameworks to evaluate the ethical profiles of LLMs before deployment in sensitive applications.
  2. 2Incorporate ethical profiling into the model selection and fine-tuning process for LLMs.
  3. 3Develop guidelines for LLM behavior based on desired virtue profiles for specific use cases.
  4. 4Educate AI development teams on virtue ethics and its application in LLM evaluation.

Original post by Ioannis Tzachristas, John Pavlopoulos

"arXiv:2606.28683v1 Announce Type: new Abstract: Large Language Models (LLMs) often face ethical tradeoffs in which several responses may be defensible but express different priorities, such as fairness, honesty, courage, or restraint. We introduce VirtueMap, a framework for descr…"

View on X

Originally posted by Ioannis Tzachristas, John Pavlopoulos on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research

AI Engineering & DevToolsAI ResearchAI News & Tools

GLM-5.3 Model Demonstrates Advanced Coding and Cyber Capabilities

The GLM-5.3 model has been unveiled, showcasing advanced capabilities in frontier coding and emergent cyber operations. This development points to significant progress in AI's ability to handle complex programming tasks and potentially cybersecurity challenges.

pellaAug 14, 2026
AI Engineering & DevToolsAI ResearchAI Investing

FlowLOB Generates Realistic, Controllable Limit Order Books Efficiently

This paper introduces FlowLOB, a conditional flow-matching generator for Limit Order Book (LOB) trajectories that offers realistic market dynamics, efficient sampling, and controllable scenario generation, outperforming existing agent-based and deep generative simulators. FlowLOB achieves high fidelity with significantly fewer computational steps than diffusion models and transfers effectively to unseen instruments.

Zhuohan Wang, Andreea Bacalum, Ollie Olby, Carmine Ventre, Namid StillmanAug 14, 2026
AI Engineering & DevToolsAI Research

Auditing Reveals Bias in Neural Combinatorial Optimization Benchmarks

This paper audits test-time budget allocation in Neural Combinatorial Optimization (NCO) solvers, revealing that reported gains from non-uniform sampling often stem from "sampling luck" rather than true allocation benefits on in-distribution data. It proposes a correction procedure and demonstrates real gains under distribution shift, emphasizing the need for rigorous evaluation.

Jinhyung BaeAug 14, 2026