Towards Machines that Trust: AI Agents Learn to Trust in the Trust Game

• URL: http://arxiv.org/abs/2312.12868v1
• Date: Wed, 20 Dec 2023 09:32:07 GMT
• Title: Towards Machines that Trust: AI Agents Learn to Trust in the Trust Game
• Authors: Ardavan S. Nobandegani, Irina Rish, Thomas R. Shultz
• Abstract summary: We present a theoretical analysis of the $textittrust game$, the canonical task for studying trust in behavioral and brain sciences. Specifically, leveraging reinforcement learning to train our AI agents, we investigate learning trust under various parameterizations of this task. Our theoretical analysis, corroborated by the simulations results presented, provides a mathematical basis for the emergence of trust in the trust game.
• Score: 11.788352764861369
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Widely considered a cornerstone of human morality, trust shapes many aspects of human social interactions. In this work, we present a theoretical analysis of the $\textit{trust game}$, the canonical task for studying trust in behavioral and brain sciences, along with simulation results supporting our analysis. Specifically, leveraging reinforcement learning (RL) to train our AI agents, we systematically investigate learning trust under various parameterizations of this task. Our theoretical analysis, corroborated by the simulations results presented, provides a mathematical basis for the emergence of trust in the trust game.

Related papers

• Trusting Your AI Agent Emotionally and Cognitively: Development and Validation of a Semantic Differential Scale for AI Trust [16.140485357046707]
  We develop and validated a set of 27-item semantic differential scales for affective and cognitive trust. Our empirical findings showed how the emotional and cognitive aspects of trust interact with each other and collectively shape a person's overall trust in AI agents.
  arXiv  Detail & Related papers  (2024-07-25T18:55:33Z)
• Can Large Language Model Agents Simulate Human Trust Behavior? [81.45930976132203]
  We investigate whether Large Language Model (LLM) agents can simulate human trust behavior. GPT-4 agents manifest high behavioral alignment with humans in terms of trust behavior. We also probe the biases of agent trust and differences in agent trust towards other LLM agents and humans.
  arXiv  Detail & Related papers  (2024-02-07T03:37:19Z)
• A Diachronic Perspective on User Trust in AI under Uncertainty [52.44939679369428]
  Modern NLP systems are often uncalibrated, resulting in confidently incorrect predictions that undermine user trust. We study the evolution of user trust in response to trust-eroding events using a betting game.
  arXiv  Detail & Related papers  (2023-10-20T14:41:46Z)
• Decoding trust: A reinforcement learning perspective [11.04265850036115]
  Behavioral experiments on the trust game have shown that trust and trustworthiness are universal among human beings. We turn to the paradigm of reinforcement learning, where individuals update their strategies by evaluating the long-term return through accumulated experience. In the pairwise scenario, we reveal that high levels of trust and trustworthiness emerge when individuals appreciate both their historical experience and returns in the future.
  arXiv  Detail & Related papers  (2023-09-26T01:06:29Z)
• A Mental Model Based Theory of Trust [31.14516396625931]
  We propose a mental model based theory of trust that can be used to infer trust. We then use the theory to define trust evolution, human reliance and decision making, and a formalization of the appropriate level of trust in the agent.
  arXiv  Detail & Related papers  (2023-01-29T22:36:37Z)
• Designing for Responsible Trust in AI Systems: A Communication Perspective [56.80107647520364]
  We draw from communication theories and literature on trust in technologies to develop a conceptual model called MATCH. We highlight transparency and interaction as AI systems' affordances that present a wide range of trustworthiness cues to users. We propose a checklist of requirements to help technology creators identify appropriate cues to use.
  arXiv  Detail & Related papers  (2022-04-29T00:14:33Z)
• Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient [0.0]
  The problem of human trust in artificial intelligence is one of the most fundamental problems in applied machine learning. We draw from statistical learning theory and sociological lenses on human-automation trust to motivate an AI-as-tool framework. We clarify the role of interpretability in trust with a ladder of model access.
  arXiv  Detail & Related papers  (2022-02-10T19:59:23Z)
• Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI [55.4046755826066]
  We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i.e., trust between people) We incorporate a formalization of 'contractual trust', such that trust between a user and an AI is trust that some implicit or explicit contract will hold. We discuss how to design trustworthy AI, how to evaluate whether trust has manifested, and whether it is warranted.
  arXiv  Detail & Related papers  (2020-10-15T03:07:23Z)
• Where Does Trust Break Down? A Quantitative Trust Analysis of Deep Neural Networks via Trust Matrix and Conditional Trust Densities [94.65749466106664]
  We introduce the concept of trust matrix, a novel trust quantification strategy. A trust matrix defines the expected question-answer trust for a given actor-oracle answer scenario. We further extend the concept of trust densities with the notion of conditional trust densities.
  arXiv  Detail & Related papers  (2020-09-30T14:33:43Z)
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks [94.65749466106664]
  We conduct a thought experiment and explore two key questions about trust in relation to confidence. We introduce a suite of metrics for assessing the overall trustworthiness of deep neural networks based on their behaviour when answering a set of questions. The proposed metrics are by no means perfect, but the hope is to push the conversation towards better metrics.
  arXiv  Detail & Related papers  (2020-09-12T17:37:36Z)

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.