Taking Principles Seriously: A Hybrid Approach to Value Alignment

• URL: http://arxiv.org/abs/2012.11705v1
• Date: Mon, 21 Dec 2020 22:05:07 GMT
• Title: Taking Principles Seriously: A Hybrid Approach to Value Alignment
• Authors: Tae Wan Kim, John Hooker, Thomas Donaldson
• Abstract summary: We propose that designers of value alignment (VA) systems incorporate ethics by utilizing a hybrid approach. We show how principles derived from deontological ethics imply particular "test propositions" for any given action plan in an AI rule base. This permits empirical VA to integrate seamlessly with independently justified ethical principles.
• Score: 7.75406296593749
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: An important step in the development of value alignment (VA) systems in AI is understanding how VA can reflect valid ethical principles. We propose that designers of VA systems incorporate ethics by utilizing a hybrid approach in which both ethical reasoning and empirical observation play a role. This, we argue, avoids committing the "naturalistic fallacy," which is an attempt to derive "ought" from "is," and it provides a more adequate form of ethical reasoning when the fallacy is not committed. Using quantified model logic, we precisely formulate principles derived from deontological ethics and show how they imply particular "test propositions" for any given action plan in an AI rule base. The action plan is ethical only if the test proposition is empirically true, a judgment that is made on the basis of empirical VA. This permits empirical VA to integrate seamlessly with independently justified ethical principles.

Related papers

• Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making [69.44075077934914]
  "Responsible AI" emphasizes the critical nature of addressing biases within the development of a corporate culture. This thesis is structured around three fundamental pillars: understanding bias, mitigating bias, and accounting for bias. In line with open-source principles, we have released Bias On Demand and FairView as accessible Python packages.
  arXiv  Detail & Related papers  (2024-01-13T14:07:09Z)
• EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval [43.72331337131317]
  We introduce a workflow that integrates ethical alignment with an initial ethical judgment stage for efficient data screening. We present the QA-ETHICS dataset adapted from the ETHICS benchmark, which serves as an evaluation tool by unifying scenarios and label meanings. In addition, we suggest a new approach that achieves top performance in both binary and multi-label ethical judgment tasks.
  arXiv  Detail & Related papers  (2023-10-02T08:22:34Z)
• Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? [78.3738172874685]
  Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research.
  arXiv  Detail & Related papers  (2023-08-29T15:57:32Z)
• Ethics in conversation: Building an ethics assurance case for autonomous AI-enabled voice agents in healthcare [1.8964739087256175]
  The principles-based ethics assurance argument pattern is one proposal in the AI ethics landscape. This paper presents the interim findings of a case study applying this ethics assurance framework to the use of Dora, an AI-based telemedicine system.
  arXiv  Detail & Related papers  (2023-05-23T16:04:59Z)
• Macro Ethics Principles for Responsible AI Systems: Taxonomy and Future Directions [1.864621482724548]
  We develop a taxonomy of 21 normative ethical principles which can be operationalised in AI. We envision this taxonomy will facilitate the development of methodologies to incorporate normative ethical principles in reasoning capacities of responsible AI systems.
  arXiv  Detail & Related papers  (2022-08-12T08:48:16Z)
• AiSocrates: Towards Answering Ethical Quandary Questions [51.53350252548668]
  AiSocrates is a system for deliberative exchange of different perspectives to an ethical quandary. We show that AiSocrates generates promising answers to ethical quandary questions with multiple perspectives. We argue that AiSocrates is a promising step toward developing an NLP system that incorporates human values explicitly by prompt instructions.
  arXiv  Detail & Related papers  (2022-05-12T09:52:59Z)
• 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)
• A Principles-based Ethics Assurance Argument Pattern for AI and Autonomous Systems [5.45210704757922]
  An emerging proposition within the trustworthy AI and autonomous systems (AI/AS) research community is to use assurance cases to instil justified confidence. This paper substantially develops the proposition and makes it concrete. It brings together the assurance case methodology with a set of ethical principles to structure a principles-based ethics assurance argument pattern.
  arXiv  Detail & Related papers  (2022-03-29T09:08:03Z)
• AI-Ethics by Design. Evaluating Public Perception on the Importance of Ethical Design Principles of AI [0.0]
  We investigate how ethical principles are weighted in comparison to each other. We show that different preference models for ethically designed systems exist among the German population.
  arXiv  Detail & Related papers  (2021-06-01T09:01:14Z)
• Case Study: Deontological Ethics in NLP [119.53038547411062]
  We study one ethical theory, namely deontological ethics, from the perspective of NLP. In particular, we focus on the generalization principle and the respect for autonomy through informed consent. We provide four case studies to demonstrate how these principles can be used with NLP systems.
  arXiv  Detail & Related papers  (2020-10-09T16:04:51Z)

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.