VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
Mayer, James H
7 Pith papers cite this work, alongside 9,879 external citations. Polarity classification is still indexing.
7
Pith papers citing it
9,879
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LLMs excel at retrospective mental-state labeling on naturalistic dialogues but mostly fail a context-free prospective probe that maps isolated mental-state profiles to dialogue trajectories, despite expert 100% accuracy.
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
Trust in social LLM chatbots is a dynamic, situated user state that evolves through ongoing interactions rather than forming as a stable one-time judgment.
Among novice programmers using AI code generators, trust did not predict compliance with suggestions, while performance correlated with both compliance and increased subsequent trust.
Survey and experiment with 606 analysts show regularization adoption depends on usability and community norms, not formal recommendations.
Develops the transitive trust concept and Fortress and Gatekeeper framework to explain third-party cybersecurity governance boundaries using trust and data flows, illustrated by one incident case.
citing papers explorer
-
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
-
DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories
LLMs excel at retrospective mental-state labeling on naturalistic dialogues but mostly fail a context-free prospective probe that maps isolated mental-state profiles to dialogue trajectories, despite expert 100% accuracy.
-
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
-
Trust as a Situated User State in Social LLM-Based Chatbots: A Longitudinal Study of Snapchat's My AI
Trust in social LLM chatbots is a dynamic, situated user state that evolves through ongoing interactions rather than forming as a stable one-time judgment.
-
Relationships Between Trust, Compliance, and Performance for Novice Programmers Using AI Code Generation
Among novice programmers using AI code generators, trust did not predict compliance with suggestions, while performance correlated with both compliance and increased subsequent trust.
-
Why is Regularization Underused? An Empirical Study on Trust and Adoption of Statistical Methods
Survey and experiment with 606 analysts show regularization adoption depends on usability and community norms, not formal recommendations.
-
Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance
Develops the transitive trust concept and Fortress and Gatekeeper framework to explain third-party cybersecurity governance boundaries using trust and data flows, illustrated by one incident case.