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.
Title resolution pending
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
OrchestrXR uses multi-agent orchestration with structured schemas to generate Unity XR study prototypes from ideas, supported by a user study with 12 researchers indicating effective support and intent preservation.
FeatX extracts epic-feature hierarchies with code mappings from repositories and applies feature edits via a three-stage Evolution Agent, reporting 42.6% relative F1 gain in function-level localization and lower cognitive load versus vanilla ChatGPT in a user study and 38-commit replay.
Post-generation control in AI-assisted math visual creation yields higher teacher ratings for predictability and correctness than pre- or mid-generation control, with qualitative trade-offs in agency and effort.
Elemental Alchemist generates contextual tools and abstracts particle-system parameters into semantic mid-level attributes and high-level conceptual controls, with a user study indicating it helps practitioners translate creative goals into technical edits.
LearnMate^2, an LLM-driven personalized learning support system, improves learning outcomes and user experience over existing online platforms combined with generic LLM assistance in small-scale user studies.
VRSafe adds false positive keystrokes to VR typing data to reduce keystroke inference attack accuracy and includes an efficient malicious login detector.
HolmeSketcher is a generative 3D sketching system for crime scene investigation that improves spatial accuracy and scene interpretability over 2D methods while increasing user task load.
A child-as-actor generative storytelling system updated by real-world food behavior increases preschoolers' willingness to try low-preference foods and reduces parental feeding pressure in a field study with 11 families.
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
In a 16-designer within-subjects study, LLM-generated vulnerability personas and journey stories significantly raised empathy, intrinsic motivation, usefulness, and concrete privacy findings compared with designers' usual methods.
Empirical study finds moderate automation (with correction opportunities) outperforms fully automatic support on trust, autonomy, and satisfaction in home medication routines, especially for older adults with varying digital confidence and privacy concerns.
A natural-language pipeline for authoring context-aware smart-home reminders was built and tested in two user studies (N=40, N=10) showing improved handling of complex conditions.
Industry markets AI agents for orchestration, creation, and insight, but a usability study with 31 participants reveals users face challenges from capability misalignment and lack of meta-cognition in tools like Operator and Manus.
A 2D spatial canvas that plots revisions by scientific exposition and narrative engagement helps LLM-assisted science writers iterate more reflectively and confidently.
A controlled user study with 24 programmers shows sketch-based pen input can handle breakpoint setting, step execution, and state inspection in debugging, though precision, recognition, and recall remain challenges.
An empirical study creates guidelines for interpreting the Human-Computer Trust Scale as a starting point for assessing trust propensity in technology interactions, while stressing the need for contextual reflection.
citing papers explorer
-
Comparing Human Oversight Strategies for Computer-Use Agents
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.