AiSocrates: Towards Answering Ethical Quandary Questions

• URL: http://arxiv.org/abs/2205.05989v1
• Date: Thu, 12 May 2022 09:52:59 GMT
• Title: AiSocrates: Towards Answering Ethical Quandary Questions
• Authors: Yejin Bang, Nayeon Lee, Tiezheng Yu, Leila Khalatbari, Yan Xu, Dan Su, Elham J. Barezi, Andrea Madotto, Hayden Kee, Pascale Fung
• Abstract summary: 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.
• Score: 51.53350252548668
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Considerable advancements have been made in various NLP tasks based on the impressive power of large pre-trained language models (LLMs). These results have inspired efforts to understand the limits of LLMs so as to evaluate how far we are from achieving human level general natural language understanding. In this work, we challenge the capability of LLMs with the new task of Ethical Quandary Generative Question Answering. Ethical quandary questions are more challenging to address because multiple conflicting answers may exist to a single quandary. We propose a system, AiSocrates, that provides an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle. AiSocrates searches for different ethical principles applicable to the ethical quandary and generates an answer conditioned on the chosen principles through prompt-based few-shot learning. We also address safety concerns by providing a human controllability option in choosing ethical principles. We show that AiSocrates generates promising answers to ethical quandary questions with multiple perspectives, 6.92% more often than answers written by human philosophers by one measure, but the system still needs improvement to match the coherence of human philosophers fully. We argue that AiSocrates is a promising step toward developing an NLP system that incorporates human values explicitly by prompt instructions. We are releasing the code for research purposes.

Related papers

• Exploring and steering the moral compass of Large Language Models [55.2480439325792]
  Large Language Models (LLMs) have become central to advancing automation and decision-making across various sectors. This study proposes a comprehensive comparative analysis of the most advanced LLMs to assess their moral profiles.
  arXiv  Detail & Related papers  (2024-05-27T16:49:22Z)
• Quelle {é}thique pour quelle IA ? [0.0]
  This study proposes an analysis of the different types of ethical approaches involved in the ethics of AI. The author introduces to the contemporary need for and meaning of ethics, distinguishes it from other registers of normativities and underlines its inadequacy to formalization. The study concludes with a reflection on the reasons why a human ethics of AI based on a pragmatic practice of contextual ethics remains necessary and irreducible to any formalization or automated treatment of the ethical questions that arise for humans.
  arXiv  Detail & Related papers  (2024-05-21T08:13:02Z)
• Beyond Bias and Compliance: Towards Individual Agency and Plurality of Ethics in AI [0.0]
  We argue that the way data is labeled plays an essential role in the way AI behaves. We propose an alternative path that allows for the plurality of values and the freedom of individual expression.
  arXiv  Detail & Related papers  (2023-02-23T16:33:40Z)
• ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations [81.70195684646681]
  We present ClarifyDelphi, an interactive system that learns to ask clarification questions. We posit that questions whose potential answers lead to diverging moral judgments are the most informative. Our work is ultimately inspired by studies in cognitive science that have investigated the flexibility in moral cognition.
  arXiv  Detail & Related papers  (2022-12-20T16:33:09Z)
• 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)
• 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 Word on Machine Ethics: A Response to Jiang et al. (2021) [36.955224006838584]
  We focus on a single case study of the recently proposed Delphi model and offer a critique of the project's proposed method of automating morality judgments. We conclude with a discussion of how machine ethics could usefully proceed, by focusing on current and near-future uses of technology.
  arXiv  Detail & Related papers  (2021-11-07T19:31:51Z)
• Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes [72.64975113835018]
  Motivated by descriptive ethics, we investigate a novel, data-driven approach to machine ethics. We introduce Scruples, the first large-scale dataset with 625,000 ethical judgments over 32,000 real-life anecdotes. Our dataset presents a major challenge to state-of-the-art neural language models, leaving significant room for improvement.
  arXiv  Detail & Related papers  (2020-08-20T17:34:15Z)
• Ethics of Technology needs more Political Philosophy [0.0]
  The ongoing debate on the ethics of self-driving cars typically focuses on two approaches to answering ethical questions: moral philosophy and social science. Political philosophy adds three basic concerns to our conceptual toolkit: reasonable pluralism, human agency, and legitimacy. These three concerns have so far been largely overlooked in the debate on the ethics of self-driving cars.
  arXiv  Detail & Related papers  (2020-01-10T15:27:02Z)

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.