helpResearch questionLLM Trust and Over/Under-Reliance
How can explanatory automated fact-checking tools be designed to include uncertainty, evidence quality, and reasoning processes?Direction: AI Explainability, Trust, and Calibration
LLM Trust and Over/Under-Reliance
Stats are based on currently indexed question data; missing sources remain visible.
124
items
31
sources
2025
latest
All questions
124 items
lightbulbPractical problemLLM Trust and Over/Under-Reliance
Fact-checkers struggle to keep up with GenAI-driven misinformation waves.helpResearch questionLLM Trust and Over/Under-Reliance
How do users make decisions in GenAI tools to maximize productivity?helpResearch questionLLM Trust and Over/Under-Reliance
What strategies do users adopt when deciding whether to use GenAI tools?helpResearch questionLLM Trust and Over/Under-Reliance
How can GenAI systems be designed to better optimize user decision-making and enhance productivity?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users struggle to cope with uncertainty in GenAI output quality and response time, reducing productivity.helpResearch questionLLM Trust and Over/Under-Reliance
How do blind users cope with uncertainties such as errors, incompleteness, and subjectivity when using generative AI (GenAI) tools?helpResearch questionLLM Trust and Over/Under-Reliance
How do blind users leverage generative AI, human help, and other social resources to address uncertainty in information access?helpResearch questionLLM Trust and Over/Under-Reliance
How does treating uncertainty as a normalized practice affect design and analysis of generative AI tools?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Erroneous outputs from generative AI tools increase information access challenges for blind users.helpResearch questionLLM Trust and Over/Under-Reliance
How can dynamically selecting and presenting LLM-generated analyses improve decision-makers' appropriate reliance on AI recommendations and decision accuracy?helpResearch questionLLM Trust and Over/Under-Reliance
How do different presentation modes (sequential vs. simultaneous) of LLM analyses affect human decision-making?helpResearch questionLLM Trust and Over/Under-Reliance
How can computational models of human behavior optimize information presentation for more efficient and intelligent human-AI interaction?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users either over-rely on or ignore AI recommendations, degrading decision quality.helpResearch questionLLM Trust and Over/Under-Reliance
In group decision-making, can dynamic LLM devil's advocate designs improve decision accuracy?helpResearch questionLLM Trust and Over/Under-Reliance
Can a devil's advocate role critiquing AI recommendations reduce over-reliance on AI?helpResearch questionLLM Trust and Over/Under-Reliance
How do different devil's advocate designs (e.g., static vs. dynamic, targeting AI vs. majority opinion) affect group discussion quality?lightbulbPractical problemLLM Trust and Over/Under-Reliance
In group decision-making, members easily blindly trust AI recommendations, leading to wrong decisions.helpResearch questionLLM Trust and Over/Under-Reliance
How does GenAI affect users' productivity (e.g., performance, efficiency, satisfaction) in programming tasks?helpResearch questionLLM Trust and Over/Under-Reliance
How has users' trust in GenAI changed over time and across task contexts?helpResearch questionLLM Trust and Over/Under-Reliance
What behavioral differences do experts and novices show when using GenAI-assisted tools?lightbulbPractical problemLLM Trust and Over/Under-Reliance
When programming with GenAI, users struggle to identify erroneous suggestions, and misplaced trust reduces efficiency.helpResearch questionLLM Trust and Over/Under-Reliance
How can large language models (LLMs) optimize document retrieval and ranking performance without fine-tuning?CUI '24"Advancing Faithfulness of Large Language Models in Goal-Oriented Dialogue Question Answering"
helpResearch questionLLM Trust and Over/Under-Reliance
In task-oriented conversational QA, how can introducing self-reflection mechanisms reduce hallucinated (inaccurate) generated content?CUI '24"Advancing Faithfulness of Large Language Models in Goal-Oriented Dialogue Question Answering"
helpResearch questionLLM Trust and Over/Under-Reliance
How can multi-document retrieval and answer generation be effectively combined to improve conversational system trustworthiness (based on retrieval accuracy)?CUI '24"Advancing Faithfulness of Large Language Models in Goal-Oriented Dialogue Question Answering"
lightbulbPractical problemLLM Trust and Over/Under-Reliance
Current conversational systems struggle to generate accurate and reliable responses when relying on external knowledge.CUI '24"Advancing Faithfulness of Large Language Models in Goal-Oriented Dialogue Question Answering"
helpResearch questionLLM Trust and Over/Under-Reliance
What specific personality dimensions does GPT-3 express during user interaction?helpResearch questionLLM Trust and Over/Under-Reliance
Are GPT-3's personality dimensions consistent with traditional psychological models (e.g., the Big Five)?helpResearch questionLLM Trust and Over/Under-Reliance
How do users perceive different personality dimensions of GPT-3 during interaction?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users struggle to achieve naturalness and trust when interacting with conversational AI.helpResearch questionLLM Trust and Over/Under-Reliance
Can live programming reduce developers' cognitive load when verifying correctness of AI-generated code?helpResearch questionLLM Trust and Over/Under-Reliance
How does live programming affect developers' behavior when selecting and verifying multiple AI code suggestions?helpResearch questionLLM Trust and Over/Under-Reliance
Can introducing live programming improve trust and efficiency of AI-assisted programming tools?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Developers struggle to quickly verify AI-generated code correctness, leading to low efficiency or tool distrust.helpResearch questionLLM Trust and Over/Under-Reliance
How do GenAI tools (e.g., ChatGPT and DALL-E) affect technology adoption and trust among resource-constrained community entrepreneurs?helpResearch questionLLM Trust and Over/Under-Reliance
What support systems can help entrepreneurs in poor and marginalized communities overcome technology anxiety and use GenAI effectively?helpResearch questionLLM Trust and Over/Under-Reliance
How can community-led collaborative design models enhance entrepreneurs' skill mastery and psychological adaptation to GenAI?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Entrepreneurs in poor and marginalized communities struggle to understand or trust GenAI tools.helpResearch questionLLM Trust and Over/Under-Reliance
How can UX be designed for the unique characteristics of GenAI?helpResearch questionLLM Trust and Over/Under-Reliance
How should GenAI design principles be adjusted to enhance user trust and collaboration efficiency?helpResearch questionLLM Trust and Over/Under-Reliance
Which design strategies can reduce potential harm GenAI may cause users?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users encounter obstacles when using GenAI due to insufficient trust or model complexity.helpResearch questionLLM Trust and Over/Under-Reliance
How can user interfaces help users efficiently identify hallucinated content in LLMs such as ChatGPT?helpResearch questionLLM Trust and Over/Under-Reliance
Which design features (e.g., confidence scores, source links) significantly improve users' ability to detect hallucinations?helpResearch questionLLM Trust and Over/Under-Reliance
How can interaction design balance users' trust in AI tools with vigilance about potential hallucinations?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users easily over-trust LLM outputs even when they may contain hallucinations.helpResearch questionLLM Trust and Over/Under-Reliance
What are the specific values and risks of generative AI (e.g., LLMs) in writing assistance?helpResearch questionLLM Trust and Over/Under-Reliance
How do users perceive the financial value of generative AI writing assistants and their impact on writing experience?helpResearch questionLLM Trust and Over/Under-Reliance
How do generative AI assistance modes across writing scenarios affect users' writing performance, trust, and satisfaction?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users often worry about reduced creative control and sense of ownership when using AI writing assistants.Related papers
IUI 2025
A Dynamic Bayesian Network Based Framework for Multimodal Context-Aware Interactions
Violet Yinuo Han, Tianyi Wang, Hyunsung Cho
IUI 2025
Mental Models of Generative AI Chatbot Ecosystem
Xingyi Wang, Xiaozheng Wang, Sunyup Park
IUI 2025
Building Appropriate Mental Models: What Users Know and Want to Know about an Agentic AI Chatbot
Michelle Brachman, Siya Kunde, Sarah Miller
CHI 2025
To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models
Jessica Y Bo, Sophia Wan, Ashton Anderson
CHI 2025
Emerging Data Practices: Data Work in the Era of Large Language Models
Adriana Alvarado Garcia, Heloisa Candello, Karla Badillo-Urquiola
CHI 2025
Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation
SeongYeub Chu, JongWoo Kim, Mun Yong Yi
CHI 2025
Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant
Gaole He, Gianluca Demartini, Ujwal Gadiraju
CHI 2025
Effects of LLM-based Search on Decision Making: Speed, Accuracy, and Overreliance
Sofia Eleni Spatharioti, David Rothschild, Daniel G. Goldstein
CHI 2025
Generative AI in Documentary Photography: Exploring Opportunities and Challenges for Visual Storytelling
Lenny Martinez, Baptiste Caramiaux, Sarah Fdili Alaoui
CHI 2025
Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages
Shreyan Biswas, Alexander Erlei, Ujwal Gadiraju
CHI 2025
Understanding the Dynamics in Deploying AI-Based Content Creation Support Tools in Broadcasting Systems - Benefits, Challenges, and Directions
Joon Gi Chung, Soongi Hong, Junho Choi
CHI 2025
Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies
Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao
Adjacent categories
AI Explainability, Trust, and Calibration
Uncertainty Communication and Calibrated Reliance
127 items
AI Explainability, Trust, and Calibration
Medical AI Trust, Clinical Decision Support, and Patient-Provider Collaboration
124 items
AI Explainability, Trust, and Calibration
XAI Explanation and Appropriate Reliance Calibration
101 items
AI Explainability, Trust, and Calibration
Explanation Form Design and Comprehension Effects
100 items
AI Explainability, Trust, and Calibration
Transparency, Auditability, and Trust Calibration Mechanisms
72 items
AI Explainability, Trust, and Calibration
Trust in Conversational AI and Chatbots
71 items
AI Explainability, Trust, and Calibration
AI Decision Support and Reliance Behavior
56 items
AI Explainability, Trust, and Calibration
Misinformation, Content Labeling, and Authenticity Trust
49 items