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

TL;DR

EthicMind is a framework for multi-turn dialogue that dynamically balances ethical safety and emotional engagement by analyzing risk and user emotion at each turn without extra training.

Contribution

It introduces a risk-aware, turn-level decision framework for ethical-emotional alignment in dialogue systems, evaluated with a new multi-turn, risk-stratified protocol.

Findings

EthicMind achieves more consistent ethical guidance.

It maintains emotional engagement effectively.

Performs well in high-risk, morally ambiguous scenarios.

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.