# Decolonial AI Alignment: Openness, Vi'sedsa-Dharma, and Including Excluded Knowledges

arXiv: https://arxiv.org/abs/2309.05030 · HTML: https://mlsanity.com/paper/2309.05030/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 145 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition](https://mlsanity.com/paper/2307.13269/) (2023)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Auditing large language models: a three-layered approach](https://mlsanity.com/paper/2302.08500/) (2023)
- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [Racial categories in machine learning](https://mlsanity.com/paper/1811.11668/) (2018)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [The Forgotten Margins of AI Ethics](https://mlsanity.com/paper/2205.04221/) (2022)
- [Building Socio-culturally Inclusive Stereotype Resources with Community Engagement](https://mlsanity.com/paper/2307.10514/) (2023)
- [The Multi-fidelity Multi-armed Bandit](https://mlsanity.com/paper/1610.09726/) (2016)
- [Learning Norms from Stories: A Prior for Value Aligned Agents](https://mlsanity.com/paper/1912.03553/) (2019)
- [Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context](https://mlsanity.com/paper/2006.09663/) (2020)
- [Pretrained AI Models: Performativity, Mobility, and Change](https://mlsanity.com/paper/1909.03290/) (2019)
- [Broadening AI Ethics Narratives: An Indic Art View](https://mlsanity.com/paper/2204.03789/) (2022)
- [Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue](https://mlsanity.com/paper/2208.09174/) (2022)

## Built on by (most cited first, 10 of 10)

- [Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations](https://mlsanity.com/paper/2403.09704/) (2024)
- [A taxonomy of epistemic injustice in the context of AI and the case for generative hermeneutical erasure](https://mlsanity.com/paper/2504.07531/) (2025)
- [FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models](https://mlsanity.com/paper/2511.18852/) (2025)
- [Do Chinese models speak Chinese languages?](https://mlsanity.com/paper/2504.00289/) (2025)
- [BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture](https://mlsanity.com/paper/2511.03180/) (2025)
- [Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions](https://mlsanity.com/paper/2604.21871/) (2026)
- [LKValues: Aligning Large Language Models with Sri Lankan Societal Values](https://mlsanity.com/paper/2607.20410/) (2026)
- [Think Outside the Data: Colonial Biases and Systemic Issues in Automated Moderation Pipelines for Low-Resource Languages](https://mlsanity.com/paper/2501.13836/) (2025)
- [What Do People Actually Want From AI? Mapping Preference Plurality](https://mlsanity.com/paper/2606.06674/) (2026)
- [Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture](https://mlsanity.com/paper/2609.35302/) (2026)

## Abstract (arXiv)

Prior work has explicated the coloniality of artificial intelligence (AI) development and deployment through mechanisms such as extractivism, automation, sociological essentialism, surveillance, and containment. However, that work has not engaged much with alignment: teaching behaviors to a large language model (LLM) in line with desired values, and has not considered a mechanism that arises within that process: moral absolutism -- a part of the coloniality of knowledge. Colonialism has a history of altering the beliefs and values of colonized peoples; in this paper, I argue that this history is recapitulated in current LLM alignment practices and technologies. Furthermore, I suggest that AI alignment be decolonialized using three forms of openness: openness of models, openness to society, and openness to excluded knowledges. This suggested approach to decolonial AI alignment uses ideas from the argumentative moral philosophical tradition of Hinduism, which has been described as an open-source religion. One concept used is vi'sedsa-dharma, or particular context-specific notions of right and wrong. At the end of the paper, I provide a suggested reference architecture to work toward the proposed framework.