HCI.TOPHCI, made easy

arrow_backBack to questions View categoryarrow_forward

LLM and Natural Language Interaction / Dialogue System Management and Error Handling

How can users' negative behaviors be captured in real time during multi-turn dialogue and dialogue strategies dynamically adjusted?

helpResearch questionDialogue System Management and Error Handling

How can users' negative behaviors be captured in real time during multi-turn dialogue and dialogue strategies dynamically adjusted?

UbiComp '21Adaptor: A Real-time Module for a Conversational Agent to Adapt Policy Based on Negative User Behavior

Similar questions

helpResearch questionDialogue System Management and Error Handling

How do different memory cues (e.g., personal photos and nostalgic objects) affect older adults' reminiscence behavior?

CHI '25Chorus of the Past: Toward Designing a Multi-agent Conversational Reminiscence System with Digital Artifacts for Older Adults

helpResearch questionDialogue System Management and Error Handling

How can a multi-identity AI dialogue system be designed to optimize older adults' reminiscence experiences?

CHI '25Chorus of the Past: Toward Designing a Multi-agent Conversational Reminiscence System with Digital Artifacts for Older Adults

helpResearch questionDialogue System Management and Error Handling

How does dynamic topic switching affect the naturalness of dialogue systems?

CHI '25Chorus of the Past: Toward Designing a Multi-agent Conversational Reminiscence System with Digital Artifacts for Older Adults

helpResearch questionDialogue System Management and Error Handling

How can hidden NLP errors be efficiently diagnosed in automated order-processing dialogue systems?

CHI '25Diagnosing and Prioritizing Issues in Automated Order-Taking Systems: A Machine-Assisted Error Discovery Approach

helpResearch questionDialogue System Management and Error Handling

Which errors have the greatest impact on key metrics such as automation rate and customer experience?

CHI '25Diagnosing and Prioritizing Issues in Automated Order-Taking Systems: A Machine-Assisted Error Discovery Approach

helpResearch questionDialogue System Management and Error Handling

How can a cross-modal general-purpose analysis tool extend to other conversational AI application scenarios?

CHI '25Diagnosing and Prioritizing Issues in Automated Order-Taking Systems: A Machine-Assisted Error Discovery Approach

Related papers

Chorus of the Past: Toward Designing a Multi-agent Conversational Reminiscence System with Digital Artifacts for Older Adults

Jingwei Sun, Zhongyue Zhang, Mengyang Wang

Diagnosing and Prioritizing Issues in Automated Order-Taking Systems: A Machine-Assisted Error Discovery Approach

Maeda F Hanafi, Frederick Reiss, Yannis Katsis

SCAINs Presenter: Preventing Miscommunication by Detecting Context-Dependent Utterances in Spoken Dialogue

Aoto Tsuchiya, Tomoyuki Maekawa, Michita Imai

“As an AI language model, I cannot”: Investigating LLM Denials of User Requests

Joel Wester, Tim Schrills, Henning Pohl

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues

Ye Liu, Stefan Ultes, Wolfgang Minker