Explainable ethical assessment on human behaviors by generating conflicting social norms
Publication Type
Conference Proceeding Article
Publication Date
12-2025
Abstract
Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action report a witnessed crime are social norms that inform our conduct, such as It is expected to be brave to report crimes. Current AI systems that assess valence (i.e., support or oppose) of human actions by leveraging large-scale data training not grounded on explicit norms may be difficult to explain, and thus untrustworthy. Emulating human assessors by considering social norms can help AI models better understand and predict valence. While multiple norms come into play, conflicting norms can create tension and directly influence human behavior. For example, when deciding whether to report a witnessed crime, one may balance bravery against self-protection. In this paper, we introduce ClarityEthic, a novel ethical assessment approach, to enhance valence prediction and explanation by generating conflicting social norms behind human actions, which strengthens the moral reasoning capabilities of language models by using a contrastive learning strategy. Extensive experiments demonstrate that our method outperforms strong baseline approaches, and human evaluations confirm that the generated social norms provide plausible explanations for the assessment of human behaviors.
Discipline
Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
Proceedings of the 14th International Joint Conference on Natural Language Processing (IJCNLP) and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), Mumbai, India, 2025 December 20-24
First Page
1
Last Page
19
Identifier
10.48550/arXiv.2512.15793
City or Country
Mumbai, India
Citation
SUN, Yuxi; GAO, Wei; LIN, Hongzhan; MA, Jing; and ZHANG, Wenxuan.
Explainable ethical assessment on human behaviors by generating conflicting social norms. (2025). Proceedings of the 14th International Joint Conference on Natural Language Processing (IJCNLP) and The 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), Mumbai, India, 2025 December 20-24. 1-19.
Available at: https://ink.library.smu.edu.sg/sis_research/10829
Additional URL
https://doi.org/10.48550/arXiv.2512.15793