EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue
2026-04-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how dialogue systems can better handle tricky conversations involving emotions and ethics at the same time. They created EthicMind, a system that makes thoughtful decisions each time it responds by looking at both the user's feelings and any ethical risks. Without extra training, EthicMind plans replies that balance being kind and morally correct across multiple back-and-forth exchanges. Tests show it works better than other methods especially when conversations get complex or risky.
dialogue systemsempathyethical judgmentmulti-turn dialoguerisk-aware frameworksemotional engagementethical riskresponse strategyuser simulationinference time
Authors
Jiawen Deng, Wei Li, Wentao Zhang, Ziyun Jiao, Fuji Ren
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.