Testing for completions that simulate altruism in early language models

No abstract is available for this paper.

• Publication year

  2025

• Venue

  Nature Human Behaviour

• Publication date

  2025-07-28

• Fields of study

  Medicine, Linguistics, Psychology

• Identifiers
  DOI 10.1038/s41562-025-02258-7PMID 40721508
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Language-based game theory in the age of artificial intelligence

  2024cited by this paper
• A Turing test of whether AI chatbots are behaviorally similar to humans

  2024cited by this paper
• AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

  2023cited by this paper
• Of Models and Tin Men - a behavioural economics study of principal-agent problems in AI alignment using large-language models

  2023cited by this paper
• Role play with large language models

  2023cited by this paper
• Evidence of behavior consistent with self-interest and altruism in an artificially intelligent agent

  2023cited by this paper
• Can AI language models replace human participants?

  2023cited by this paper
• From Outcome-Based to Language-Based Preferences

  2022cited by this paper
• Aligning to Social Norms and Values in Interactive Narratives

  2022cited by this paper
• Out of One, Many: Using Language Models to Simulate Human Samples

  2022cited by this paper
• Using cognitive psychology to understand GPT-3

  2022cited by this paper
• Performance vs. competence in human–machine comparisons

  2020cited by this paper
• PALM: Pre-training an Autoencoding&autoregressive Language Model for Context-conditioned Generation

  2020cited by this paper
• Life 3.0: being human in the age of artificial intelligence

  2019cited by this paper
• Machine behaviour

  2019cited by this paper
• Superintelligence: Paths, Dangers, Strategies

  2017cited by this paper
• Cooperating with machines

  2017cited by this paper
• A Unified Approach to Interpreting Model Predictions

  2017cited by this paper
• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier

  2016cited by this paper
• Major evolutionary transitions in individuality

  2015influential reference
• Invited Review SPECIAL ISSUE: Using Ideas from Behavioural Ecology to Understand Plants

  2015cited by this paper
• Leakage in data mining: formulation, detection, and avoidance

  2011cited by this paper
• Anthropomorphism and AI: Turingʼs much misunderstood imitation game

  2011cited by this paper
• Dictator games: a meta study

  2011influential reference
• Evolutionary foundations of human prosocial sentiments

  2011cited by this paper
• Altruism, Spite, and Greenbeards

  2010cited by this paper
• The Social Lives of Microbes

  2007cited by this paper
• Kin recognition in an annual plant

  2007cited by this paper
• Costly Punishment Across Human Societies

  2006cited by this paper
• The Altruism Equation

  2006cited by this paper
• Five Rules for the Evolution of Cooperation

  2006influential reference
• Chimpanzees are indifferent to the welfare of unrelated group members

  2005cited by this paper
• The nature of human altruism

  2003cited by this paper
• Altruistic punishment in humans

  2002cited by this paper
• Cooperation and Punishment in Public Goods Experiments

  2000cited by this paper
• Fairness in Simple Bargaining Experiments

  1994cited by this paper
• Fairness and the Assumptions of Economics

  1986cited by this paper
• An experimental analysis of ultimatum bargaining

  1982influential reference
• Altruism and Related Phenomena, Mainly in Social Insects

  1972cited by this paper
• The genetical evolution of social behaviour. I.

  1964cited by this paper
• The genetical evolution of social behaviour. II.

  1964cited by this paper
• The Evolution of Altruistic Behavior

  1963cited by this paper

• Humanlike AI Design Increases Anthropomorphism but Yields Divergent Outcomes on Engagement and Trust Globally

  2025cites this paper