Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
Title resolution pending
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
WhatIf provides an interactive platform for real-time exploration of LLM-driven social simulations, enabling policymakers to iteratively test plans, reflect on assumptions, and uncover vulnerabilities in emergency preparedness scenarios.
This paper proposes a five-dimension ethical design space for front-end biometric translation in sensor-fused health AI agents, including adaptive disclosure as a guardrail against hallucinations and biofeedback loops.
Schemex is an interactive three-stage AI workflow for schema induction that user studies show produces more actionable schemas than a frontier baseline without loss of generalizability.
Users entangle their lived experiences with AI predictions in menstrual tracking apps, leading to self-fulfilling prophecies, limited critical awareness from UI, and isolation for non-normative users.
Expert mathematicians using an AI coding agent for discovery engage in repeated cycles of intentmaking to define goals and sensemaking to interpret outputs.
Analysis of Canada's Federal AI Register reveals it frames AI as reliable internal tooling by obscuring sociotechnical elements like human discretion, turning transparency into performative compliance.
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
Speed-dating storyboard study finds misaligned teacher-student views on AI control, trust, and social-emotional learning in K-12 classrooms.
A qualitative study of a provotype shows that adding transparency and control features to AI recommender interfaces helps users understand personalization, address filter bubble concerns, and build trust.
citing papers explorer
-
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
-
Guidelines for Designing AI Technologies to Support Adult Learning
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
-
WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning
WhatIf provides an interactive platform for real-time exploration of LLM-driven social simulations, enabling policymakers to iteratively test plans, reflect on assumptions, and uncover vulnerabilities in emergency preparedness scenarios.
-
Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for Biometrics
This paper proposes a five-dimension ethical design space for front-end biometric translation in sensor-fused health AI agents, including adaptive disclosure as a guardrail against hallucinations and biofeedback loops.
-
Schemex: Discovering Structural Abstractions from Examples
Schemex is an interactive three-stage AI workflow for schema induction that user studies show produces more actionable schemas than a frontier baseline without loss of generalizability.
-
"It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps
Users entangle their lived experiences with AI predictions in menstrual tracking apps, leading to self-fulfilling prophecies, limited critical awareness from UI, and isolation for non-normative users.
-
Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
Expert mathematicians using an AI coding agent for discovery engage in repeated cycles of intentmaking to define goals and sensemaking to interpret outputs.
-
Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures
Analysis of Canada's Federal AI Register reveals it frames AI as reliable internal tooling by obscuring sociotechnical elements like human discretion, turning transparency into performative compliance.
-
"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
-
Mind the Trust Gap: Identifying (Mis)alignments in Teacher-Student Views Toward Control and Agency in K-12 Classroom AI
Speed-dating storyboard study finds misaligned teacher-student views on AI control, trust, and social-emotional learning in K-12 classrooms.
-
Rethinking User Empowerment in AI Recommender System: Innovating Transparent and Controllable Interfaces
A qualitative study of a provotype shows that adding transparency and control features to AI recommender interfaces helps users understand personalization, address filter bubble concerns, and build trust.