lightbulb现实痛点LLM使用不满、策略调整与满意度虚拟助手难以准确理解和反应用户的情感,从而降低其可信度。IUI '25Advancing Affective Intelligence in Virtual Agents Using Affect Control Theory
lightbulb现实痛点LLM使用不满、策略调整与满意度用户不清楚生成式AI在创意任务中的真实能力,影响协作表现。CHI '25CreAItive Collaboration? Users' Misjudgment of AI-Creativity Affects Their Collaborative Performance
lightbulb现实痛点LLM使用不满、策略调整与满意度知识工作者可能因依赖生成式AI而丧失批判性思维能力。CHI '25The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge Workers
lightbulb现实痛点LLM使用不满、策略调整与满意度用户可能被大语言模型生成的心理操控设计模式误导。CHI '25"Create a Fear of Missing Out" – ChatGPT Implements Unsolicited Deceptive Designs in Generated Websites Without Warning
lightbulb现实痛点LLM使用不满、策略调整与满意度自闭症群体在负面自我对话中往往缺乏有效的支持工具。CHI '25Reimagining Support: Exploring Autistic Individuals' Visions for AI in Coping with Negative Self-Talk
lightbulb现实痛点LLM使用不满、策略调整与满意度在线辩论中,生成式AI可能导致信息偏误、误导内容传播及用户体验不协调。CHI '25"Ronaldo's a poser!": How the Use of Generative AI Shapes Debates in Online Forums
lightbulb现实痛点LLM使用不满、策略调整与满意度用户对ChatGPT在理解意图、内容深度和准确性方面表现不满。IUI '24Analyzing User Dissatisfaction with ChatGPT Responses: Types, Resolution Strategies, and the Impact of Knowledge Levels
lightbulb现实痛点LLM使用不满、策略调整与满意度AI心理健康工具受西方文化偏向限制,难以满足不同地区用户需求。CSCW '24Towards Culturally Adaptive Large Language Models in Mental Health: Using ChatGPT as a Case Study
lightbulb现实痛点LLM使用不满、策略调整与满意度现有日记应用难以满足用户深度情感反思和社交分享的需求。UbiComp '24Music Diary: Using ChatGPT to Craft Interactive Diaries with Emotional Music for Reflection and Sharing Real-life Emotions
lightbulb现实痛点LLM使用不满、策略调整与满意度Alexa用户遇到技能政策违规或功能失效,但问题难以及时被发现。UbiComp '24End-Users Know Best: Identifying Undesired Behavior of Alexa Skills Through User Review Analysis
lightbulb现实痛点LLM使用不满、策略调整与满意度用户可能基于聊天机器人使用的代词感知到不符合预期的社会身份。CHI '24Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPT
lightbulb现实痛点LLM使用不满、策略调整与满意度用户难以甄别聊天代理中的错误信息,可能导致过度信任和错误传播。CHI '24Empowering Calibrated (Dis-)Trust in Conversational Agents: A User Study on the Persuasive Power of Limitation Disclaimers vs. Authoritative Style
lightbulb现实痛点LLM使用不满、策略调整与满意度程序员越来越依赖ChatGPT回答技术问题,但其误导性信息可能导致代码缺陷。CHI '24Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions
lightbulb现实痛点LLM使用不满、策略调整与满意度年轻的知识工作者害怕AI工具取代他们的角色,削弱成就感。CHI '24"If the Machine Is As Good As Me, Then What Use Am I?" – How the Use of ChatGPT Changes Young Professionals' Perception of Productivity and Accomplishment
lightbulb现实痛点LLM使用不满、策略调整与满意度自闭症个体难以独立处理日常问题或获得情感支持。CHI '24Unlock Life with a Chat(GPT): Integrating Conversational AI with Large Language Models into Everyday Lives of Autistic Individuals
lightbulb现实痛点LLM使用不满、策略调整与满意度初级学者在压力下难以高效且准确地利用大型语言模型完成复杂学术任务。CHI '24Evaluating Large Language Models on Academic Literature Understanding and Review: An Empirical Study among Early-stage Scholars
lightbulb现实痛点LLM使用不满、策略调整与满意度用户不知道如何充分利用 ChatGPT 来提高效率或解决问题。CUI '23The User Experience of ChatGPT: Findings From a Questionnaire Study of Early Users
lightbulb现实痛点LLM使用不满、策略调整与满意度用户在复杂任务中难以有效组织和总结由AI生成的大量信息。UIST '23Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models
lightbulb现实痛点LLM使用不满、策略调整与满意度研究者难以接触弱势群体,且传统场景设计耗时费力。CSCW '23Toward Value Scenario Generation Through Large Language Models
lightbulb现实痛点LLM使用不满、策略调整与满意度用户在新任务环境下难以高效选择交互策略。CHI '22Computational Rationality as a Theory of Interaction