mlsanityData to 14 Oct 2026

EMNLP: Educator-role Moral and Normative Large Language Models Profiling

arXiv 2508.15250 ↗First posted 21 Aug 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Simulating Professions (SP) enables Large Language Models (LLMs) to emulate professional roles. However, comprehensive psychological and ethical evaluation in these contexts remains lacking. This paper introduces EMNLP, an Educator-role Moral and Normative LLMs Profiling framework for personality profiling, moral development stage measurement, and ethical risk under soft prompt injection. EMNLP extends existing scales and constructs 88 teacher-specific moral dilemmas, enabling profession-oriented comparison with human teachers. A targeted soft prompt injection set evaluates compliance and vulnerability in teacher SP. Experiments on 14 LLMs show teacher-role LLMs exhibit more idealized and polarized personalities than human teachers, excel in abstract moral reasoning, but struggle with emotionally complex situations. Models with stronger reasoning are more vulnerable to harmful prompt injection, revealing a paradox between capability and safety. The model temperature and other hyperparameters have limited influence except in some risk behaviors. This paper presents the first benchmark to assess ethical and psychological alignment of teacher-role LLMs for educational AI. Resources are available at https://e-m-n-l-p.github.io/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 41 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

15 of 41 references.

References · 15

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  3. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  4. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  5. 2024Simulating Classroom Education with LLM-Empowered Agentscited by 127
  6. 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Servicescited by 120
  7. 2022Who is GPT-3? An Exploration of Personality, Values and Demographicscited by 112
  8. 2023DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultationcited by 90
  9. 2023Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizationscited by 61
  10. 2024Personalized Large Language Modelscited by 44
  11. 2024Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humanscited by 11
  12. 2024Evaluating Moral Beliefs across LLMs through a Pluralistic Frameworkcited by 11
3 more
  1. 2024GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoningcited by 9
  2. 2024A Multi-Task Role-Playing Agent Capable of Imitating Character Linguistic Stylescited by 6
  3. 2024Chat Bankman-Fried: an Exploration of LLM Alignment in Financecited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers
  2. 2026Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
  3. 2023Potential Benefits of Employing Large Language Models in Research in Moral Education and Development
  4. 2024Exploring and steering the moral compass of Large Language Models
  5. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  6. 2025Differences in the Moral Foundations of Large Language Models
  7. 2024MoralBench: Moral Evaluation of LLMs
  8. 2026Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture