Workshop participants preferred bounded, faithful AI agents that evolve only while the user retains capacity and then remain static, leading to a proposal that configuration for post-capacity use reshapes provenance, temporality, and legitimacy in post-mortem agent design.
hub
In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany)(CHI ’23, Article 111)
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
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.
Specific human-AI personality pairings causally affect collaboration quality and downstream performance in a preregistered experiment with 1,258 participants, 7,266 ads, and nearly 5 million impressions.
DroidRetriever is a transparent steerable mobile automation system that decomposes information-seeking tasks with multi-LLM agents, navigates apps, synthesizes reports with screenshots, and provides a dashboard for real-time user intervention and privacy pauses.
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
Older adults with MCC adapted physical token input visualizations to track health data, using them for immediate pattern reflection, routine integration, and personal expression during a two-week study.
Filter Babel explores a future of AI-personalized private experiences that may erode common ground in communication while supporting individual identity and selfhood.
Structural mental models of AI writing assistants improve system understanding and usability but result in more grammatical errors in user writing compared to functional models.
An online study of 70 students found that gender, race, and self-efficacy predict distinct ChatGPT query patterns during essay writing, with patterns linked to enjoyment and perceived ownership of the final essay.
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.
citing papers explorer
-
Acts of Configuration: Rethinking Provenance, Temporality and Legitimacy in Post-Mortem Agents
Workshop participants preferred bounded, faithful AI agents that evolve only while the user retains capacity and then remain static, leading to a proposal that configuration for post-capacity use reshapes provenance, temporality, and legitimacy in post-mortem agent design.
-
Towards Measuring the Representation of Subjective Global Opinions in Language Models
LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
-
Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs
Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
-
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.
-
Personality Pairing Improves Human-AI Collaboration
Specific human-AI personality pairings causally affect collaboration quality and downstream performance in a preregistered experiment with 1,258 participants, 7,266 ads, and nearly 5 million impressions.
-
DroidRetriever: A Transparent and Steerable Automation System for Collaborative Mobile Information Seeking
DroidRetriever is a transparent steerable mobile automation system that decomposes information-seeking tasks with multi-LLM agents, navigates apps, synthesizes reports with screenshots, and provides a dashboard for real-time user intervention and privacy pauses.
-
A Roadmap to Pluralistic Alignment
The paper formalizes three types of pluralistic AI models and three benchmark classes, arguing that current alignment techniques may reduce rather than increase distributional pluralism.
-
Input Visualizations to Track Health Data by Older Adults with Multiple Chronic Conditions
Older adults with MCC adapted physical token input visualizations to track health data, using them for immediate pattern reflection, routine integration, and personal expression during a two-week study.
-
Filter Babel: The Challenge of Synthetic Media to Authenticity and Common Ground in AI-Mediated Communication
Filter Babel explores a future of AI-personalized private experiences that may erode common ground in communication while supporting individual identity and selfhood.
-
From Use to Oversight: How Mental Models Influence User Behavior and Output in AI Writing Assistants
Structural mental models of AI writing assistants improve system understanding and usability but result in more grammatical errors in user writing compared to functional models.
-
An Empirical Study to Understand How Students Use ChatGPT for Writing Essays
An online study of 70 students found that gender, race, and self-efficacy predict distinct ChatGPT query patterns during essay writing, with patterns linked to enjoyment and perceived ownership of the final essay.
-
Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.