An argument paper reframes LLM explainability as an embodied, situated practice based on Dourish and enactivist cognition, identifying ontological obstacles in internal explanations and advocating affordance-based designs.
hub
Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems , articleno =
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
A single algorithm for online multicalibration achieves instance-adaptive rates by dynamically refining a dyadic prediction grid, recovering the worst-case Õ(T^{2/3}) bound and improving to Õ(√T) in marginal stochastic settings and Õ(√(JT)) for J-piecewise stationary means.
IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
Summary reasoning traces from LLMs maintain task performance and increase trust and appeal relative to answer-only or full-trace conditions, but none of the formats improve users' metacognitive calibration on reasoning tasks.
Two linked user studies find that LLM rationale correctness and certainty framing affect trust and decision confidence while presentation format does not, and incorrect rationales increase gaze attention and pupil size.
The paper proposes six interconnected elements of a design space to close the synergy gap in human-AI decision-making.
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
Mixed-methods study finds AI assistance linked to higher textual overlap with suggestions in writing tasks, and a reflective interface prototype increases user awareness of AI incorporation.
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.
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.
Automated classification of CPS discourse combined with the Synergy Degree Model produces group-level synergy degrees that distinguish collaborative quality and reveal task-type differences in MOOC groups.
Position paper proposing Model Science as a discipline to systematically analyze AI model behavior beyond benchmarks, drawing analogies from cognitive science, neuroscience, medicine, and agriculture.
citing papers explorer
-
Embodied Explainability and Ontological Obstacles: Why We Struggle to Explain the Answers of Large Language Models (LLMs)
An argument paper reframes LLM explainability as an embodied, situated practice based on Dourish and enactivist cognition, identifying ontological obstacles in internal explanations and advocating affordance-based designs.
-
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
-
Instance-Adaptive Online Multicalibration
A single algorithm for online multicalibration achieves instance-adaptive rates by dynamically refining a dyadic prediction grid, recovering the worst-case Õ(T^{2/3}) bound and improving to Õ(√T) in marginal stochastic settings and Õ(√(JT)) for J-piecewise stationary means.
-
IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI
IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
-
Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and Metacognition
Summary reasoning traces from LLMs maintain task performance and increase trust and appeal relative to answer-only or full-trace conditions, but none of the formats improve users' metacognitive calibration on reasoning tasks.
-
When LLM Rationales Become User-Facing: Effects on Trust Perception, Decision-Making, and Gaze Behaviors
Two linked user studies find that LLM rationale correctness and certainty framing affect trust and decision confidence while presentation format does not, and incorrect rationales increase gaze attention and pupil size.
-
Addressing the Synergy Gap: The Six Elements of the Design Space
The paper proposes six interconnected elements of a design space to close the synergy gap in human-AI decision-making.
-
Position: AI as Part of Self -- Extending the Mind Requires Cognitive Co-Regulation
The paper claims that alignment requires treating AI as part of the self through cognitive co-regulation, identifying risks like deskilling and automation bias while drawing on System 0 cognition theory.
-
Overreliance in Writing Tasks: Exploring Similarity-Based Measures of AI Influence on Writing and Proposing a Reflective Writing Interface Intervention
Mixed-methods study finds AI assistance linked to higher textual overlap with suggestions in writing tasks, and a reflective interface prototype increases user awareness of AI incorporation.
-
Evaluating the False Trust Engendered by LLM Explanations
LLM reasoning traces and post-hoc explanations increase false trust in incorrect predictions, whereas contrastive dual explanations enhance users' ability to distinguish correct from incorrect AI outputs.
-
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.
-
Modeling Collaborative Problem Solving Dynamics from Group Discourse: A Text-Mining Approach with Synergy Degree Model
Automated classification of CPS discourse combined with the Synergy Degree Model produces group-level synergy degrees that distinguish collaborative quality and reveal task-type differences in MOOC groups.
-
The Case for Model Science: Verify, Explore, Steer, Refine
Position paper proposing Model Science as a discipline to systematically analyze AI model behavior beyond benchmarks, drawing analogies from cognitive science, neuroscience, medicine, and agriculture.