The Goofus & Gallant Story Corpus for Practical Value Alignment

• URL: http://arxiv.org/abs/2501.09707v1
• Date: Thu, 16 Jan 2025 17:58:58 GMT
• Title: The Goofus & Gallant Story Corpus for Practical Value Alignment
• Authors: Md Sultan Al Nahian, Tasmia Tasrin, Spencer Frazier, Mark Riedl, Brent Harrison,
• Abstract summary: Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules. As AI systems are becoming ubiquitous in human society, it is a major concern that they could violate these norms or values and potentially cause harm. This work presents a multi-modal dataset illustrating normative and non-normative behavior in real-life situations.
• Score: 2.0938191327156037
• License:
• Abstract: Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules to maintain social order. As AI systems are becoming ubiquitous in human society, it is a major concern that they could violate these norms or values and potentially cause harm. Thus, to prevent intentional or unintentional harm, AI systems are expected to take actions that align with these principles. Training systems to exhibit this type of behavior is difficult and often requires a specialized dataset. This work presents a multi-modal dataset illustrating normative and non-normative behavior in real-life situations described through natural language and artistic images. This training set contains curated sets of images that are designed to teach young children about social principles. We argue that this is an ideal dataset to use for training socially normative agents given this fact.

Related papers

• The Reasonable Person Standard for AI [0.0]
  The American legal system often uses the "Reasonable Person Standard" This paper argues that the reasonable person standard provides useful guidelines for the type of behavior we should develop, probe, and stress-test in models.
  arXiv  Detail & Related papers  (2024-06-07T06:35:54Z)
• 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)
• "One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors [57.63649797577999]
  We conduct case studies in which we perturb different types of identity-related language features (names, roles, locations, dialect, and style) in NLG system inputs. We find that motivations for adaptation include social norms, cultural differences, feature-specific information, and accommodation. In contrast, motivations for invariance include perspectives that favor prescriptivism, view adaptation as unnecessary or too difficult for NLG systems to do appropriately, and are wary of false assumptions.
  arXiv  Detail & Related papers  (2023-10-23T23:00:34Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)
• Aligning to Social Norms and Values in Interactive Narratives [89.82264844526333]
  We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games. We introduce the GALAD agent that uses the social commonsense knowledge present in specially trained language models to contextually restrict its action space to only those actions that are aligned with socially beneficial values.
  arXiv  Detail & Related papers  (2022-05-04T09:54:33Z)
• Learning Norms via Natural Language Teachings [0.0]
  This paper introduces and demonstrates a computational approach to learning norms from natural language text. It provides a foundation for everyday people to train AI systems about social norms.
  arXiv  Detail & Related papers  (2022-01-20T22:09:42Z)
• Toward a Theory of Justice for Artificial Intelligence [2.28438857884398]
  It holds that the basic structure of society should be understood as a composite of socio-technical systems. As a consequence, egalitarian norms of justice apply to the technology when it is deployed in these contexts.
  arXiv  Detail & Related papers  (2021-10-27T13:23:38Z)
• Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences [36.884156839960184]
  We investigate whether contemporary NLG models can function as behavioral priors for systems deployed in social settings. We introduce 'Moral Stories', a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning.
  arXiv  Detail & Related papers  (2020-12-31T17:28:01Z)
• Social Chemistry 101: Learning to Reason about Social and Moral Norms [73.23298385380636]
  We present Social Chemistry, a new conceptual formalism to study people's everyday social norms and moral judgments. Social-Chem-101 is a large-scale corpus that catalogs 292k rules-of-thumb. Our model framework, Neural Norm Transformer, learns and generalizes Social-Chem-101 to successfully reason about previously unseen situations.
  arXiv  Detail & Related papers  (2020-11-01T20:16:45Z)
• Hacia los Comit\'es de \'Etica en Inteligencia Artificial [68.8204255655161]
  It is priority to create the rules and specialized organizations that can oversight the following of such rules. This work proposes the creation, at the universities, of Ethical Committees or Commissions specialized on Artificial Intelligence.
  arXiv  Detail & Related papers  (2020-02-11T23:48:31Z)

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.