Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs

Abhinav Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, Monojit Choudhury


Abstract
In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided with an ethical policy, an LLM should be capable of making decisions that are ethically consistent to the policy. We develop a framework that integrates moral dilemmas with moral principles pertaining to different foramlisms of normative ethics, and at different levels of abstractions. Initial experiments with GPT-x models shows that while GPT-4 is a nearly perfect ethical reasoner, the models still have bias towards the moral values of Western and English speaking societies.
Anthology ID:
2023.findings-emnlp.892
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13370–13388
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.892
DOI:
10.18653/v1/2023.findings-emnlp.892
Bibkey:
Cite (ACL):
Abhinav Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, and Monojit Choudhury. 2023. Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13370–13388, Singapore. Association for Computational Linguistics.
Cite (Informal):
Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs (Rao et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.892.pdf