TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.
Canonical reference
ISBN 9781450367080
Canonical reference. 100% of citing Pith papers cite this work as background.
citation-role summary
citation-polarity summary
roles
background 8polarities
background 8representative citing papers
Survey evidence shows VR privacy deception exploits cognitive and ergonomic vulnerabilities, increasing acceptance of invasive data practices framed as immersion-preserving and fostering privacy resignation.
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
PlotChain benchmark reports top MLLMs reaching ~80% field-level accuracy on engineering plot reading under human-like tolerances, but with persistent failures on frequency-domain tasks like bandpass and FFT spectra.
Older Korean immigrants use pragmatic disengagement to avoid stressful technologies and interdependent navigation where digital skills are shared family resources, treating non-use as culturally grounded data refusal.
Decomposer fine-tunes on synthetic Strudel-MIDI pairs then applies RL on unpaired MIDI to produce faithful yet readable music programs, outperforming LLMs and heuristics on reconstruction and readability.
Episodic framing of text in mass shooting data visualizations elicits more negative emotions than thematic framing and indirectly increases support for gun control policies.
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.
HealthTale automatically converts patients' freeform narratives into structured timelines grouped by health concern and time, with preliminary evidence that patients and clinicians find the artifacts useful for first clinical encounters.
Narrix helps novices identify and reuse narrative strategies from examples through visualization and strategy-steered generation, improving retention, confidence, and adaptation over chat interfaces in a 12-person study.
Qualitative study of 19 CS students using multi-view visualizations reveals selective engagement driven by agency, fit, and legitimacy rather than cognitive load reduction alone.
A literature review concludes that pursuing consensus in data annotation creates biased AI by dismissing subjective disagreements and enforcing geographic hegemony, and proposes mapping diversity instead.
Interviews reveal a four-stage vibe coding workflow that accelerates prototyping while introducing tensions between quick efficiency and reflective design intention, plus asymmetries in trust and ownership.
A user study found that portable physical surfaces improve precision, efficiency, and bimanual use in VR touch tasks compared to visual-only or vibrotactile feedback.
Qualitative study of 17 interviews finds digital tools support labor organizing but introduce challenges in technical security, information overload, and building trust and consensus.
Qualitative studies show creatives prefer self-experimentation over structured guidance for GenAI image tools to preserve creative autonomy despite terminology barriers.
A design study develops DanteExploreVis, a VA tool for historical book trade data, using a variant of the Nine-Stage Framework and qualitative evaluation with domain experts.
citing papers explorer
-
TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents
TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.
-
Rushed by Discomfort, Trapped by Immersion: Users' Experiences and Responses to Privacy Deceptive Design in Commercial VR Applications
Survey evidence shows VR privacy deception exploits cognitive and ergonomic vulnerabilities, increasing acceptance of invasive data practices framed as immersion-preserving and fostering privacy resignation.
-
Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
-
PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading
PlotChain benchmark reports top MLLMs reaching ~80% field-level accuracy on engineering plot reading under human-like tolerances, but with persistent failures on frequency-domain tasks like bandpass and FFT spectra.
-
Interdependent Navigation and Pragmatic Disengagement: How Older Korean Immigrants Selectively Engage with Digital Technologies
Older Korean immigrants use pragmatic disengagement to avoid stressful technologies and interdependent navigation where digital skills are shared family resources, treating non-use as culturally grounded data refusal.
-
Decomposer: Learning to Decompile Symbolic Music to Programs
Decomposer fine-tunes on synthetic Strudel-MIDI pairs then applies RL on unpaired MIDI to produce faithful yet readable music programs, outperforming LLMs and heuristics on reconstruction and readability.
-
Comparing the Emotional Impact of Thematic Versus Episodic Framing in Visualization Text
Episodic framing of text in mass shooting data visualizations elicits more negative emotions than thematic framing and indirectly increases support for gun control policies.
-
HolmeSketcher: Generative 3D Sketch Mapping for Spatial Reconstruction in Crime Scene Investigation
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.
-
HealthTale: A Patient-Centric Health Story Visualization Tool
HealthTale automatically converts patients' freeform narratives into structured timelines grouped by health concern and time, with preliminary evidence that patients and clinicians find the artifacts useful for first clinical encounters.
-
Narrix: Remixing Narrative Strategies from Examples for Story Writing
Narrix helps novices identify and reuse narrative strategies from examples through visualization and strategy-steered generation, improving retention, confidence, and adaptation over chat interfaces in a 12-person study.
-
Code as Anchor, Memory and Metaphor as Support: Learner Experiences with Multi-View Visualizations
Qualitative study of 19 CS students using multi-view visualizations reveals selective engagement driven by agency, fit, and legitimacy rather than cognitive load reduction alone.
-
The Consensus Trap: Dissecting Subjectivity and the "Ground Truth" Illusion in Data Annotation
A literature review concludes that pursuing consensus in data annotation creates biased AI by dismissing subjective disagreements and enforcing geographic hegemony, and proposes mapping diversity instead.
-
Vibe Coding in Product Teams: Reconfiguring AI-Assisted Workflows, Prototyping, and Collaboration
Interviews reveal a four-stage vibe coding workflow that accelerates prototyping while introducing tensions between quick efficiency and reflective design intention, plus asymmetries in trust and ownership.
-
Physical surfaces make touch interactions in virtual reality precise, efficient, and bimanual
A user study found that portable physical surfaces improve precision, efficiency, and bimanual use in VR touch tasks compared to visual-only or vibrotactile feedback.
-
Organizing in the Digital Age: Understanding Community, Challenges, and Consequences in Digitally-facilitated Labor Organizing
Qualitative study of 17 interviews finds digital tools support labor organizing but introduce challenges in technical security, information overload, and building trust and consensus.
-
How Creatives Approach GenAI Image Generation: Tensions Between Structured Guidance, Self-Experimentation, and Creative Autonomy
Qualitative studies show creatives prefer self-experimentation over structured guidance for GenAI image tools to preserve creative autonomy despite terminology barriers.
-
Visualizing Historical Book Trade Data: An Iterative Design Study with Close Collaboration with Domain Experts
A design study develops DanteExploreVis, a VA tool for historical book trade data, using a variant of the Nine-Stage Framework and qualitative evaluation with domain experts.