EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue

2026-04-10

AI Summary

Current dialogue systems struggle to dynamically balance emotional resonance and ethical safety across multi-turn interactions. This work proposes EthicMind, a novel framework that formalizes ethical–emotional alignment as a turn-by-turn decision-making problem. During inference, EthicMind jointly perceives user emotions and ethical risks, plans high-level response strategies, and generates replies that simultaneously provide ethical guidance and emotional engagement. Notably, the framework requires no additional training and incorporates a risk-stratified multi-turn evaluation protocol alongside a context-aware user simulation mechanism. Experimental results demonstrate that EthicMind significantly outperforms baseline models in high-risk and morally ambiguous scenarios, achieving consistent improvements in both ethical alignment and emotional engagement, thereby validating its effectiveness and robustness.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: Emotional Intelligence

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or ethical judgment can cause significant harm. Existing dialogue models typically address empathy and ethical safety in isolation, and often fail to adapt their behavior as ethical risk and user emotion evolve across multi-turn interactions. We formulate ethical-emotional alignment in dialogue as an explicit turn-level decision problem, and propose \textsc{EthicMind}, a risk-aware framework that implements this formulation in multi-turn dialogue at inference time. At each turn, \textsc{EthicMind} jointly analyzes ethical risk signals and user emotion, plans a high-level response strategy, and generates context-sensitive replies that balance ethical guidance with emotional engagement, without requiring additional model training. To evaluate alignment behavior under ethically complex interactions, we introduce a risk-stratified, multi-turn evaluation protocol with a context-aware user simulation procedure. Experimental results show that \textsc{EthicMind} achieves more consistent ethical guidance and emotional engagement than competitive baselines, particularly in high-risk and morally ambiguous scenarios.

Problem

• ethical-emotional alignment
• multi-turn dialogue
• ethical risk
• empathy
• dialogue systems

Innovation

• ethical-emotional alignment
• risk-aware dialogue
• multi-turn inference
• context-sensitive response
• user simulation