Decolonial AI Alignment: Openness, Viśe\d{s}a-Dharma, and Including Excluded Knowledges

• URL: http://arxiv.org/abs/2309.05030v3
• Date: Thu, 2 May 2024 21:19:21 GMT
• Title: Decolonial AI Alignment: Openness, Viśe\d{s}a-Dharma, and Including Excluded Knowledges
• Authors: Kush R. Varshney,
• Abstract summary: I argue that colonialism has a history of altering the beliefs and values of colonized peoples. I suggest that AI alignment be decolonialized using three forms of openness. One concept used is vi'sedsa-dharma, or context-specific notions of right and wrong.
• Score: 22.21928139733195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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\'{s}e\d{s}a-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.

Related papers

• Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks [55.2480439325792]
  This paper critically examines the European Union's Artificial Intelligence Act (EU AI Act) Uses insights from Alignment Theory (AT) research, which focuses on the potential pitfalls of technical alignment in Artificial Intelligence. As we apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.
  arXiv  Detail & Related papers  (2024-10-10T17:38:38Z)
• Decolonial AI as Disenclosure [0.0]
  Machine learning and AI engender 'AI colonialism', a term that conceptually overlaps with 'data colonialism', as a form of injustice. Politically, it enforces digital capitalism's hegemony. Ecologically, it negatively impacts the environment and intensifies the extraction of natural resources and consumption of energy.
  arXiv  Detail & Related papers  (2024-05-23T09:45:37Z)
• A Material Lens on Coloniality in NLP [57.63027898794855]
  Coloniality is the continuation of colonial harms beyond "official" colonization. We argue that coloniality is implicitly embedded in and amplified by NLP data, algorithms, and software.
  arXiv  Detail & Related papers  (2023-11-14T18:52:09Z)
• Towards a Feminist Metaethics of AI [0.0]
  I argue that these insufficiencies could be mitigated by developing a research agenda for a feminist metaethics of AI. Applying this perspective to the context of AI, I suggest that a feminist metaethics of AI would examine: (i) the continuity between theory and action in AI ethics; (ii) the real-life effects of AI ethics; (iii) the role and profile of those involved in AI ethics; and (iv) the effects of AI on power relations through methods that pay attention to context, emotions and narrative.
  arXiv  Detail & Related papers  (2023-11-10T13:26:45Z)
• AI Alignment: A Comprehensive Survey [70.35693485015659]
  AI alignment aims to make AI systems behave in line with human intentions and values. We identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality. We decompose current alignment research into two key components: forward alignment and backward alignment.
  arXiv  Detail & Related papers  (2023-10-30T15:52:15Z)
• Fairness in Agreement With European Values: An Interdisciplinary Perspective on AI Regulation [61.77881142275982]
  This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. We identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns.
  arXiv  Detail & Related papers  (2022-06-08T12:32:08Z)
• Metaethical Perspectives on 'Benchmarking' AI Ethics [81.65697003067841]
  Benchmarks are seen as the cornerstone for measuring technical progress in Artificial Intelligence (AI) research. An increasingly prominent research area in AI is ethics, which currently has no set of benchmarks nor commonly accepted way for measuring the 'ethicality' of an AI system. We argue that it makes more sense to talk about 'values' rather than 'ethics' when considering the possible actions of present and future AI systems.
  arXiv  Detail & Related papers  (2022-04-11T14:36:39Z)
• Confucius, Cyberpunk and Mr. Science: Comparing AI ethics between China and the EU [41.19326726478421]
  A major concern is the large homogeneity and presumed consensualism around these principles. We propose to analyse and compare the ethical principles endorsed by the Chinese National New Generation Artificial Intelligence Governance Professional Committee and those elaborated by the European High-level Expert Group on AI (HLEGAI) In our analysis, we wish to highlight that principles that seem similar a priori may actually have different meanings, derived from different approaches and reflect distinct goals.
  arXiv  Detail & Related papers  (2021-11-15T06:38:33Z)
• Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence [6.202104487394354]
  This paper explores the role of critical science in understanding and shaping the ongoing advances in artificial intelligence. Decolonial theories use historical hindsight to explain patterns of power that shape our intellectual, political, economic, and social world. We highlight problematic applications that are instances of coloniality, and using a decolonial lens, submit three tactics that can form a decolonial field of artificial intelligence.
  arXiv  Detail & Related papers  (2020-07-08T12:36:21Z)
• Artificial Intelligence, Values and Alignment [2.28438857884398]
  normative and technical aspects of the AI alignment problem are interrelated. It is important to be clear about the goal of alignment. The central challenge for theorists is not to identify 'true' moral principles for AI.
  arXiv  Detail & Related papers  (2020-01-13T10:32:16Z)
• Learning from Learning Machines: Optimisation, Rules, and Social Norms [91.3755431537592]
  It appears that the area of AI that is most analogous to the behaviour of economic entities is that of morally good decision-making. Recent successes of deep learning for AI suggest that more implicit specifications work better than explicit ones for solving such problems.
  arXiv  Detail & Related papers  (2019-12-29T17:42:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.