Moral Responsibility for AI Systems

• URL: http://arxiv.org/abs/2310.18040v1
• Date: Fri, 27 Oct 2023 10:37:47 GMT
• Title: Moral Responsibility for AI Systems
• Authors: Sander Beckers
• Abstract summary: Moral responsibility for an outcome of an agent who performs some action is commonly taken to involve both a causal condition and an epistemic condition. This paper presents a formal definition of both conditions within the framework of causal models.
• Score: 8.919993498343159
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As more and more decisions that have a significant ethical dimension are being outsourced to AI systems, it is important to have a definition of moral responsibility that can be applied to AI systems. Moral responsibility for an outcome of an agent who performs some action is commonly taken to involve both a causal condition and an epistemic condition: the action should cause the outcome, and the agent should have been aware -- in some form or other -- of the possible moral consequences of their action. This paper presents a formal definition of both conditions within the framework of causal models. I compare my approach to the existing approaches of Braham and van Hees (BvH) and of Halpern and Kleiman-Weiner (HK). I then generalize my definition into a degree of responsibility.

Related papers

• A theory of appropriateness with applications to generative artificial intelligence [56.23261221948216]
  We need to understand how appropriateness guides human decision making in order to properly evaluate AI decision making and improve it. This paper presents a theory of appropriateness: how it functions in human society, how it may be implemented in the brain, and what it means for responsible deployment of generative AI technology.
  arXiv  Detail & Related papers  (2024-12-26T00:54:03Z)
• Technology as uncharted territory: Contextual integrity and the notion of AI as new ethical ground [55.2480439325792]
  I argue that efforts to promote responsible and ethical AI can inadvertently contribute to and seemingly legitimize this disregard for established contextual norms. I question the current narrow prioritization in AI ethics of moral innovation over moral preservation.
  arXiv  Detail & Related papers  (2024-12-06T15:36:13Z)
• Causal Responsibility Attribution for Human-AI Collaboration [62.474732677086855]
  This paper presents a causal framework using Structural Causal Models (SCMs) to systematically attribute responsibility in human-AI systems. Two case studies illustrate the framework's adaptability in diverse human-AI collaboration scenarios.
  arXiv  Detail & Related papers  (2024-11-05T17:17:45Z)
• 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)
• If our aim is to build morality into an artificial agent, how might we begin to go about doing so? [0.0]
  We discuss the different aspects that should be considered when building moral agents, including the most relevant moral paradigms and challenges. We propose solutions including a hybrid approach to design and a hierarchical approach to combining moral paradigms.
  arXiv  Detail & Related papers  (2023-10-12T12:56:12Z)
• 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)
• Bad, mad, and cooked: Moral responsibility for civilian harms in human-AI military teams [0.0]
  This chapter explores moral responsibility for civilian harms by human-artificial intelligence (AI) teams. increasingly militaries may 'cook' their good apples by putting them in untenable decision-making environments. This chapter offers new mechanisms to map out conditions for moral responsibility in human-AI teams.
  arXiv  Detail & Related papers  (2022-10-31T10:18:20Z)
• When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment [96.77970239683475]
  AI systems need to be able to understand, interpret and predict human moral judgments and decisions. A central challenge for AI safety is capturing the flexibility of the human moral mind. We present a novel challenge set consisting of rule-breaking question answering.
  arXiv  Detail & Related papers  (2022-10-04T09:04:27Z)
• Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making [8.688778020322758]
  We measure people's perceptions of eight different notions of moral responsibility concerning AI and human agents. We show that AI agents are held causally responsible and blamed similarly to human agents for an identical task. We find that people expect both AI and human decision-makers and advisors to justify their decisions regardless of their nature.
  arXiv  Detail & Related papers  (2021-02-01T04:07:38Z)
• Hiding Behind Machines: When Blame Is Shifted to Artificial Agents [0.0]
  This article focuses on the responsibility of agents who decide on our behalf. We investigate whether the production of moral outcomes by an agent is systematically judged differently when the agent is artificial and not human.
  arXiv  Detail & Related papers  (2021-01-27T14:50:02Z)
• Reinforcement Learning Under Moral Uncertainty [13.761051314923634]
  An ambitious goal for machine learning is to create agents that behave ethically. While ethical agents could be trained by rewarding correct behavior under a specific moral theory, there remains widespread disagreement about the nature of morality. This paper proposes two training methods that realize different points among competing desiderata, and trains agents in simple environments to act under moral uncertainty.
  arXiv  Detail & Related papers  (2020-06-08T16:40:12Z)

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.