helpResearch questionLLM Trust and Over/Under-Reliance
How can multimodal interaction systems integrate dynamic Bayesian networks (real-time inference tools) and large language models (contextual knowledge generation) to adapt to complex scenarios?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
helpResearch questionLLM Trust and Over/Under-Reliance
How do dynamic Bayesian networks perform real-time inference and handle uncertainty when multimodal sensor inputs are noisy?helpResearch questionLLM Trust and Over/Under-Reliance
How can multimodal interaction systems achieve scalability and adaptability in large-scale dynamic environments?lightbulbPractical problemLLM Trust and Over/Under-Reliance
When operating multi-sensor smart devices, environments are complex and misoperations occur frequently.helpResearch questionLLM Trust and Over/Under-Reliance
How do users understand data flows and privacy protection in generative AI (GenAI) chatbot ecosystems?helpResearch questionLLM Trust and Over/Under-Reliance
How do user trust and privacy concerns differ between first-party systems (e.g., Google Gemini) and third-party systems (e.g., ChatGPT)?helpResearch questionLLM Trust and Over/Under-Reliance
How do different mental models affect users' trust and data privacy decisions?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users struggle to understand complex AI ecosystems, affecting privacy decisions.helpResearch questionLLM Trust and Over/Under-Reliance
How do users use and interact with agentic generative AI systems with complex goals?helpResearch questionLLM Trust and Over/Under-Reliance
How does users' understanding of system behavior transparency and internal logic affect their trust and decision-making?helpResearch questionLLM Trust and Over/Under-Reliance
How can agentic AI systems better meet users' varying information needs for explanatory content?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Ordinary users cannot effectively understand the behavioral logic and information sources of complex generative AI.helpResearch questionLLM Trust and Over/Under-Reliance
How can interventions be designed to reduce users' over-reliance or under-reliance on large language models (LLM)?helpResearch questionLLM Trust and Over/Under-Reliance
How do different interventions (e.g., reliance disclaimers, uncertainty labels, and implicit answers) affect user trust and appropriate reliance behavior?helpResearch questionLLM Trust and Over/Under-Reliance
What factors influence users' trust calibration toward LLM advice across different task types?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users' inability to appropriately trust LLMs leads to wrong decisions or missed opportunities.helpResearch questionLLM Trust and Over/Under-Reliance
What are the main data governance and processing challenges in large language model (LLM) development?helpResearch questionLLM Trust and Over/Under-Reliance
How are data practices at different development stages influenced by LLM characteristics?helpResearch questionLLM Trust and Over/Under-Reliance
How do practitioners handle uncertainty in data processing to advance LLM development?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Practitioners struggle to manage the large-scale, complex data required for LLM development.helpResearch questionLLM Trust and Over/Under-Reliance
What limitations do current LLM-based text evaluation methods have?helpResearch questionLLM Trust and Over/Under-Reliance
How can a more comprehensive and reliable text evaluation framework combine human and LLM strengths?helpResearch questionLLM Trust and Over/Under-Reliance
How much improvement can a framework combining human and LLM strengths achieve in summarization and essay evaluation tasks?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Existing text evaluation systems have limited coverage and unreliable results, affecting education and news generation applications.helpResearch questionLLM Trust and Over/Under-Reliance
How do user involvement levels affect trust calibration and task performance for LLM (large language model) planning and execution across task contexts?helpResearch questionLLM Trust and Over/Under-Reliance
How can trust, task performance, and user cognitive load be balanced when users are involved in LLM planning and execution?helpResearch questionLLM Trust and Over/Under-Reliance
How reliable are LLMs in high-risk tasks (e.g., financial trading), and can user involvement significantly reduce error rates?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users struggle to trust and correctly use AI assistants in high-risk tasks, potentially causing errors or losses.helpResearch questionLLM Trust and Over/Under-Reliance
How do LLM search tools affect user efficiency, accuracy, and decision quality on complex queries?helpResearch questionLLM Trust and Over/Under-Reliance
Can confidence visual feedback mechanisms such as color coding reduce over-reliance on low-confidence information?helpResearch questionLLM Trust and Over/Under-Reliance
Under what conditions do LLM-generated errors significantly increase users' decision error rates?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users relying on LLM tools may depend on incorrect information and make poor decisions.helpResearch questionLLM Trust and Over/Under-Reliance
How can generative AI be integrated into documentary photography practice while upholding ethical standards?helpResearch questionLLM Trust and Over/Under-Reliance
What are the potentials and limitations of generative AI for improving community narrative transparency and participation?helpResearch questionLLM Trust and Over/Under-Reliance
How do existing generative AI tools affect the authenticity of documentary imagery and its role in social narratives?lightbulbPractical problemLLM Trust and Over/Under-Reliance
The authenticity and credibility of AI-generated images in photojournalism are difficult to trust.helpResearch questionLLM Trust and Over/Under-Reliance
Do multilingual LLMs violate the independence of irrelevant alternatives principle, and how does this affect user behavior?helpResearch questionLLM Trust and Over/Under-Reliance
How does LLM performance in low-resource languages such as Spanish change user trust in LLMs in high-resource languages such as English?helpResearch questionLLM Trust and Over/Under-Reliance
How do cultural and gender factors affect user attitudes toward AI-generated content and social behaviors such as donation?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users struggle to trust LLMs in multilingual environments, affecting cross-language collaboration and productivity.helpResearch questionLLM Trust and Over/Under-Reliance
What use cases and challenges does generative AI face in real broadcasting workflows?helpResearch questionLLM Trust and Over/Under-Reliance
How do broadcasting professionals perceive and use generative AI tools, and what problems arise?helpResearch questionLLM Trust and Over/Under-Reliance
How can generative AI tools be designed to better fit multi-party collaboration and user needs?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Broadcasting practitioners have low trust in generative AI tools and struggle to integrate them into complex workflows.helpResearch questionLLM Trust and Over/Under-Reliance
How do users determine trust in large language models (LLMs) based on features such as explanations, citations, and consistency?helpResearch questionLLM Trust and Over/Under-Reliance
How do system explanations, cited sources, and output consistency affect reliance on incorrect versus correct information?helpResearch questionLLM Trust and Over/Under-Reliance
Can highlighting inconsistency in output quality effectively reduce users' over-reliance on incorrect LLM outputs?lightbulbPractical problemLLM Trust and Over/Under-Reliance
Users easily over-trust incorrect information from LLMs, leading to decision errors.helpResearch questionLLM Trust and Over/Under-Reliance
How does increased misinformation complexity from LLMs and GenAI affect fact-checkers' workflows?helpResearch questionLLM Trust and Over/Under-Reliance
What specific explainability needs do fact-checkers have for AI tools?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