A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment

Edward Y Chang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7332-7350, 2025.

Abstract

This paper introduces a checks-and-balances framework for ethical alignment of Large Language Models (LLMs), inspired by three-branch governmental systems. It implements three independent yet interacting components: LLMs as the executive branch for knowledge generation, DIKE as the legislative branch establishing ethical guardrails, and ERIS as the judicial branch for contextual interpretation. Beyond structural separation, we address a fundamental challenge: regulating emotion to shape behaviors. Drawing from psychological theories where managing emotional responses prevents harmful behaviors, we develop a self-supervised learning pipeline that maps emotions to linguistic behaviors, enabling precise behavioral modulation through emotional conditioning. By integrating this approach with adversarial testing, our framework demonstrates how DIKE and ERIS direct linguistic behaviors toward ethical outcomes while preserving independence throughout knowledge generation, ethical oversight, and contextual interpretation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chang25a, title = {A Checks-and-Balances Framework for Context-Aware Ethical {AI} Alignment}, author = {Chang, Edward Y}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {7332--7350}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chang25a/chang25a.pdf}, url = {https://proceedings.mlr.press/v267/chang25a.html}, abstract = {This paper introduces a checks-and-balances framework for ethical alignment of Large Language Models (LLMs), inspired by three-branch governmental systems. It implements three independent yet interacting components: LLMs as the executive branch for knowledge generation, DIKE as the legislative branch establishing ethical guardrails, and ERIS as the judicial branch for contextual interpretation. Beyond structural separation, we address a fundamental challenge: regulating emotion to shape behaviors. Drawing from psychological theories where managing emotional responses prevents harmful behaviors, we develop a self-supervised learning pipeline that maps emotions to linguistic behaviors, enabling precise behavioral modulation through emotional conditioning. By integrating this approach with adversarial testing, our framework demonstrates how DIKE and ERIS direct linguistic behaviors toward ethical outcomes while preserving independence throughout knowledge generation, ethical oversight, and contextual interpretation.} }
Endnote
%0 Conference Paper %T A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment %A Edward Y Chang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chang25a %I PMLR %P 7332--7350 %U https://proceedings.mlr.press/v267/chang25a.html %V 267 %X This paper introduces a checks-and-balances framework for ethical alignment of Large Language Models (LLMs), inspired by three-branch governmental systems. It implements three independent yet interacting components: LLMs as the executive branch for knowledge generation, DIKE as the legislative branch establishing ethical guardrails, and ERIS as the judicial branch for contextual interpretation. Beyond structural separation, we address a fundamental challenge: regulating emotion to shape behaviors. Drawing from psychological theories where managing emotional responses prevents harmful behaviors, we develop a self-supervised learning pipeline that maps emotions to linguistic behaviors, enabling precise behavioral modulation through emotional conditioning. By integrating this approach with adversarial testing, our framework demonstrates how DIKE and ERIS direct linguistic behaviors toward ethical outcomes while preserving independence throughout knowledge generation, ethical oversight, and contextual interpretation.
APA
Chang, E.Y.. (2025). A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:7332-7350 Available from https://proceedings.mlr.press/v267/chang25a.html.

Related Material