Artificial Intelligence in HCI : 5th International Conference, AI-HCI 2024, Held As Part of the 26th HCI International Conference, HCII 2024, Washington, DC, USA, June 29-July 4, 2024, Proceedings, Part III
Lecture Notes in Computer Science Series ; ; v.14736
Altri autori (Persone)
NtoaStavroula
Lingua di pubblicazione
Inglese
Formato
Materiale a stampa
Livello bibliografico
Monografia
Nota di contenuto
Intro -- Foreword -- HCI International 2024 Thematic Areas and Affiliated Conferences -- List of Conference Proceedings Volumes Appearing Before the Conference -- Preface -- 5th International Conference on Artificial Intelligence in HCI (AI-HCI 2024) -- HCI International 2025 Conference -- Contents - Part III -- Large Language Models for Enhanced Interaction -- Enhancing Relation Extraction from Biomedical Texts by Large Language Models -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Relation Extraction via In-Context Few-Shot Learning with LLMs -- 3.2 Seq2seq-Based Relation Extraction Enhanced by LLMs -- 3.3 Classification-Based Relation Extraction Enhanced by LLMs -- 4 Experimental Settings -- 4.1 DDI Extraction Task Settings -- 4.2 LLMs and Prompts -- 4.3 PLMs for Seq2seq Methods -- 4.4 PLMs for Classification Methods -- 5 Results and Discussions -- 5.1 In-Context Few-Shot Learning-Based Relation Extraction by LLMs -- 5.2 Seq2seq-Based Relation Extraction Enhanced by LLMs -- 5.3 Classification-Based Relation Extraction Enhanced by LLMs -- 6 Conclusion -- References -- Using a LLM-Based Conversational Agent in the Social Robot Mini -- 1 Introduction -- 2 A Short History of Language Models -- 3 The Proposed System -- 3.1 Prompting -- 4 Integration into Mini -- 4.1 Design of the Conversational Agent Skill -- 5 Evaluation -- 6 Conclusions -- References -- A Proposal to Extend the Modeling Language for
Interaction as Conversation for the Design of Conversational Agents -- 1 Introduction -- 2 Related Work -- 2.1 Conversational Agents -- 2.2 Modeling Interaction in Conversational Agents -- 3 MoLIC -- 4 MoLIC's Limitation to Represent Conversational Agents -- 4.1 Standardized Communication Snippets -- 4.2 Transfer of Responsibility / Interlocutor During Communication -- 4.3 Modeling Breakdown Recovery -- 4.4 Conversational Agents' Intelligence.
5 Extending MoLIC -- 5.1 Template Element -- 5.2 Allowing for the Interaction with a Third-Party System -- 5.3 Adaptations to MoLIC 2.0 Elements -- 6 Initial Evaluation of Proposal -- 7 Final Remarks and Future Works -- References -- Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models' Natural Language Understanding Abilities -- 1 Introduction -- 1.1 Objectives and Research Questions -- 2 Review of Related Literature -- 3 Method and Implementation -- 3.1 Technical Architecture -- 3.2 Knowledge Base -- 3.3 Synthetic Customer Data Preparation -- 3.4 Synthetic Seller Persona Creation -- 3.5 Synthetic Sales Conversation Creation -- 4 Results -- 4.1 General Applied CoT Approach -- 4.2 Presence of Necessary Conditions -- 4.3 Product Resolution -- 4.4 Database Insertions -- 4.5 Sample Case -- 4.6 Drawbacks and Limitations -- 5 Discussions -- 6 Conclusion and Future Work -- References -- A Map of Exploring Human Interaction Patterns with LLM: Insights into Collaboration and Creativity -- 1 Introduction -- 2 Related Work -- 2.1 The Undergoing Change in HAII Driven by Large Language Model -- 2.2 The Current Review of Human-AI Interaction -- 3 Method -- 3.1 Search and Selection -- 3.2 Mapping -- 4 Result -- 4.1 Processing Tool -- 4.2 Analysis Assistant -- 4.3 Creative Companion -- 4.4 Processing Agent -- 5 Discussion -- 5.1 Mapping Methodology Based on Human and Algorithmic Approaches -- 5.2 Differences Between Clusters -- 5.3 About the Vacancy in the Mapping -- 5.4 Future Directions -- 6 Limitation and Future Work -- 7 Conclusion -- References -- The Use of Large Language Model in Code Review Automation: An Examination of Enforcing SOLID Principles -- 1 Introduction -- 2 Background -- 2.1 Code Reviews -- 2.2 SOLID Principles -- 2.3 Large Language Model Technology -- 2.4 Mixtral LLM.
2.5 Role of Bots in Code Development and Review -- 2.6 Benefits for Large Global Development Teams -- 3 Related Works -- 3.1 A Systematic Evaluation of Large Language Models of Code -- 3.2 Effects of Adopting Code Review Bots on Pull Requests to OSS Projects -- 3.3 Reducing Human Effort and Improving Quality in Peer Code Reviews Using Automatic Static Analysis and Reviewer Recommendation -- 3.4 ChatGPT: A Study of Its Utility for Common Software Engineering Tasks -- 3.5 Insights and Implications for LLM-Based Code Review -- 4 Proposed Concept -- 4.1 Proposed Architecture and Integration -- 4.2 Usage of the Proposed Bot -- 5 Impact Analysis -- 5.1 Comparison with Existing Solutions -- 5.2 Potential Benefits -- 5.3 Challenges and Limitations -- 6 Conclusion -- References -- LLM Based Multi-agent Generation of Semi-structured Documents from Semantic Templates in the Public Administration Domain -- 1 Introduction -- 2 Related Work -- 2.1 LLMs in the PA Domain -- 3 Proposed Approach -- 3.1 Template Pre-processing -- 3.2 Multi-agent Interaction -- 3.3 Document Post-processing -- 4 Experimental Evaluation -- 4.1 Semantics Identification Agent -- 4.2 Information Retrieval Agent -- 4.3 Content Generation Agent -- 4.4 Prompt-Engineered Results -- 5 Conclusions -- References -- Enabling Human-Centered Machine Translation Using Concept-Based Large Language Model Prompting and Translation Memory -- 1 Introduction -- 1.1 Challenges in Traditional Machine Translation Within Human-Computer Interaction Contexts -- 1.2
Augmented Machine Translation via Large Language Model -- 2 Augmented Machine Translation via Concept-Driven Large Language Model Prompting -- 2.1 Motivation -- 2.2 Augmented Instruction for Discourse-Level Style -- 2.3 Augmented Instruction for Concept-Based Sentence-Level Post-editing -- 2.4 Performance Evaluation.
3 Assessing the Proficiency of Large Language Model in Applying Translation Concept -- 3.1 Motivation -- 3.2 The Capability of LLMs to Elucidate Translation Concepts -- 3.3 Assessing the LLM's Proficiency in Identifying When to Apply Translation Concepts -- 3.4 The Capability of LLM to Produce Target Translations that Reflect Relevant Concepts -- 4 Conclusions -- References -- Enhancing Large Language Models Through External Domain Knowledge -- 1 Introduction -- 2 Problem Identification and Objectives -- 3 Related Works -- 4 Design and Development of the Artifact -- 4.1 Expert Knowledge Acquisition -- 4.2 Metadata Provision -- 4.3 Prompt Generation -- 5 Demonstration -- 5.1 Implementation -- 5.2 Case Study -- 6 Discussion -- References -- ChatGPT and Language Translation -- 1 Introduction -- 1.1 Historical Background - PreGPT -- 1.2 Background - LLMs and ChatGPT -- 1.3 ChatGPT and Translation -- 2 Motivation and Methodology for This Study -- 2.1 Motivation -- 2.2 Methodology -- 2.3 Examples -- 3 Results -- 3.1 Classifying AI Generated Text -- 3.2 Human Ratings of Translation Quality -- 4 Conclusions -- References -- Large Language Models for Tracking Reliability of Information Sources -- 1 Introduction -- 2 Methods -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- The Heuristic Design Innovation Approach for Data-Integrated Large Language Model -- 1 Introduction -- 2 Related Works -- 2.1 Domain-Specific LLMs -- 2.2 Expert System -- 2.3 Human-AI Collaboration Design -- 3 Method -- 3.1 Overview of DIABot -- 3.2 Prompt -- 3.3 Database -- 3.4 Workflow -- 4 Value Assessment -- 4.1 Experimental Design -- 4.2 Participants -- 4.3 Experimental Process -- 4.4 Experimental Result -- 5 Discussion and Conclusion -- 6 Limitation and Future Work -- A Prompt of DIAbot -- B Tools OpenAPI -- References -- Advancing Human-Robot Interaction Through AI.
FER-Pep: A Deep Learning Based Facial Emotion Recognition Framework for Humanoid Robot Pepper -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Pepper -- 3.2 NAOqi Python API -- 3.3 EfficientNetV2 -- 4 Dataset Collection and Preprocessing -- 5 Experiments -- 5.1 Candidate Models for Facial Emotion Recognition -- 6 System Implementation -- 7 Result and Discussion -- 8 Conclusion -- References -- You Got the Feeling: Attributing Affective States to Dialogical Social Robots -- 1 Introduction -- 2 Empathy and Emotions Theories -- 3 The Experiment -- 3.1 Method and Interaction Steps in the Dialogues -- 4 Evaluation -- 5 Results and Future Works -- References -- Enhancing Usability of Voice Interfaces for Socially Assistive Robots Through Deep Learning: A German Case Study -- 1 Introduction -- 2 Related Work -- 2.1 Voice Interface Evaluations -- 2.2 Technical Construction of Voice Interfaces -- 3 Voice Interface -- 3.1 Design Goals -- 3.2 System Description -- 4 Evaluation -- 4.1 Methods and Material -- 4.2 Participants -- 4.3 Results -- 4.4 Discussion -- 5 Limitations -- 6 Conclusion -- References -- Enhancing User Experience: Designing Intuitive Interfaces for Sumo Robot Operations -- 1 Introduction -- 1.1 Intuitive Interface -- 1.2 Robotics -- 1.3 Sumo Robots -- 1.4 Designing Intuitive Interfaces for Sumo Robot Operations -- 2 Methodology -- 3 Result -- 3.1 Sumo Robot Performance -- 3.2 User Feedback -- 4 Discussion -- 4.1 Interpretation of Results -- 4.2 Comparison with Existing System -- 4.3 Implications and Future Works -- References -- Adaptive Robotics:
Integrating Robotic Simulation, AI, Image Analysis, and Cloud-Based Digital Twin Simulation for Dynamic Task Completion -- 1 Introduction -- 1.1 Autonomous Robots -- 1.2 Robotics Simulation -- 1.3 AI in Robotics -- 1.4 Internet of Things -- 1.5 Isaac Simulation -- 1.6 Skydio and Sundt.