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

TL;DR

This paper introduces EMNLP, a framework for profiling educator-role LLMs' moral, psychological, and ethical traits, revealing their strengths and vulnerabilities compared to human teachers.

Contribution

It develops a comprehensive profiling framework and benchmark for assessing moral, psychological, and ethical aspects of teacher-role LLMs, including new dilemmas and evaluation methods.

Findings

Teacher-role LLMs show idealized, polarized personalities.

They excel in abstract moral reasoning but struggle with emotional complexity.

Stronger reasoning models are more vulnerable to harmful prompt injections.

Abstract

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/.