Proceedings of the 5th International Conference on Conversational User Interfaces最新文献_第6页

Secure, Comfortable or Functional: Exploring Domain-Sensitive Prompt Design for In-Car Voice Assistants 安全、舒适或功能:探索车载语音助手的领域敏感提示设计

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3604314

Anna-Maria Meck

引用次数: 0

Beyond Anthropomorphism: Unraveling the True Priorities of Chatbot Usage in SMEs 超越拟人化:揭示中小企业中聊天机器人使用的真正优先事项

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3604315

Tamas Makany, Sungjong Roh, Kotaro Hara, Jie Min Hua, Felicia Goh Si Ying, Wilson Teh Yang Jie

引用次数: 0

Harnessing Large Language Models for Cognitive Assistants in Factories 利用大型语言模型为工厂中的认知助手服务

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3604313

Samuel Kernan Freire, Mina Foosherian, Chaofan Wang, E. Niforatos

引用次数: 1

Misinformation in Third-party Voice Applications 第三方语音应用中的错误信息

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3604307

M. Bispham, S. Sattar, Clara Zard, Xavier Ferrer-Aran, Jide S. Edu, Guillermo Suarez-Tangil, J. Such

引用次数: 2

Understanding and Answering Incomplete Questions 理解和回答不完整的问题

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3597133

Angus Addlesee, Marco Damonte

引用次数: 5

Towards Cross-Content Conversational Agents for Behaviour Change: Investigating Domain Independence and the Role of Lexical Features in Written Language Around Change 面向行为变化的跨内容会话代理:研究领域独立性和书面语言中词汇特征在变化中的作用

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-19 DOI: 10.1145/3571884.3597136

Selina Meyer, David Elsweiler

{"title":"Towards Cross-Content Conversational Agents for Behaviour Change: Investigating Domain Independence and the Role of Lexical Features in Written Language Around Change","authors":"Selina Meyer, David Elsweiler","doi":"10.1145/3571884.3597136","DOIUrl":"https://doi.org/10.1145/3571884.3597136","url":null,"abstract":"Valuable insights into an individual’s current thoughts and stance regarding behaviour change can be obtained by analysing the language they use, which can be conceptualized using Motivational Interviewing concepts. Training conversational agents (CAs) to detect and employ these concepts could help them provide more personalized and effective assistance. This study investigates the similarity of written language around behaviour change spanning diverse conversational and social contexts and change objectives. Drawing on previous research that applied MI concepts to texts about health behaviour change, we evaluate the performance of existing classifiers on six newly constructed datasets from diverse contexts. To gain insights in determining factors when identifying change language, we explore the impact of lexical features on classification. The results suggest that patterns of change language remain stable across contexts and domains, leading us to conclude that peer-to-peer online data may be sufficient to train CAs to understand user utterances related to behaviour change.","PeriodicalId":127379,"journal":{"name":"Proceedings of the 5th International Conference on Conversational User Interfaces","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121601046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators 开放ChatGPT:跟踪指令调优文本生成器的开放性、透明度和可问责性

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-08 DOI: 10.1145/3571884.3604316

Andreas Liesenfeld, Alianda Lopez, Mark Dingemanse

{"title":"Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators","authors":"Andreas Liesenfeld, Alianda Lopez, Mark Dingemanse","doi":"10.1145/3571884.3604316","DOIUrl":"https://doi.org/10.1145/3571884.3604316","url":null,"abstract":"Large language models that exhibit instruction-following behaviour represent one of the biggest recent upheavals in conversational interfaces, a trend in large part fuelled by the release of OpenAI’s ChatGPT, a proprietary large language model for text generation fine-tuned through reinforcement learning from human feedback (LLM+RLHF). We review the risks of relying on proprietary software and survey the first crop of open-source projects of comparable architecture and functionality. The main contribution of this paper is to show that openness is differentiated, and to offer scientific documentation of degrees of openness in this fast-moving field. We evaluate projects in terms of openness of code, training data, model weights, RLHF data, licensing, scientific documentation, and access methods. We find that while there is a fast-growing list of projects billing themselves as ‘open source’, many inherit undocumented data of dubious legality, few share the all-important instruction-tuning (a key site where human annotation labour is involved), and careful scientific documentation is exceedingly rare. Degrees of openness are relevant to fairness and accountability at all points, from data collection and curation to model architecture, and from training and fine-tuning to release and deployment.","PeriodicalId":127379,"journal":{"name":"Proceedings of the 5th International Conference on Conversational User Interfaces","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126185438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues 在聊天和面向任务的对话之间具有系统启动转换的统一会话模型

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-07-04 DOI: 10.1145/3571884.3597125

Ye Liu, Stefan Ultes, W. Minker, Wolfgang Maier

{"title":"Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues","authors":"Ye Liu, Stefan Ultes, W. Minker, Wolfgang Maier","doi":"10.1145/3571884.3597125","DOIUrl":"https://doi.org/10.1145/3571884.3597125","url":null,"abstract":"Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations without special goals. Creating a unified conversational model that can engage in both chit-chat and task-oriented dialogue is a promising research topic in recent years. However, the potential “initiative” that occurs when there is a change between dialogue modes in one dialogue has rarely been explored. In this work, we investigate two kinds of dialogue scenarios, one starts from chit-chat implicitly involving task-related topics and finally switching to task-oriented requests; the other starts from task-oriented interaction and eventually changes to casual chat after all requested information is provided. We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model. One is a discrete prompt model trained with two discrete tokens, the other one is a continuous prompt model using continuous prompt embeddings automatically generated by a classifier. We furthermore show that the continuous prompt model can also be used to guide the proactive transitions between particular domains in a multi-domain task-oriented setting.","PeriodicalId":127379,"journal":{"name":"Proceedings of the 5th International Conference on Conversational User Interfaces","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128379952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Deceptive AI Ecosystems: The Case of ChatGPT 欺骗性人工智能生态系统:以ChatGPT为例

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-06-18 DOI: 10.1145/3571884.3603754

Xiao Zhan, Yifan Xu, Ş. Sarkadi

引用次数: 0

Democratizing Chatbot Debugging: A Computational Framework for Evaluating and Explaining Inappropriate Chatbot Responses 民主化聊天机器人调试:评估和解释不适当的聊天机器人响应的计算框架

Proceedings of the 5th International Conference on Conversational User Interfaces Pub Date : 2023-06-16 DOI: 10.1145/3571884.3604308

Xu Han, Michelle X. Zhou, Yichen Wang, Wenxi Chen, Tom Yeh

{"title":"Democratizing Chatbot Debugging: A Computational Framework for Evaluating and Explaining Inappropriate Chatbot Responses","authors":"Xu Han, Michelle X. Zhou, Yichen Wang, Wenxi Chen, Tom Yeh","doi":"10.1145/3571884.3604308","DOIUrl":"https://doi.org/10.1145/3571884.3604308","url":null,"abstract":"Evaluating and understanding the inappropriateness of chatbot behaviors can be challenging, particularly for chatbot designers without technical backgrounds. To democratize the debugging process of chatbot misbehaviors for non-technical designers, we propose a framework that leverages dialogue act (DA) modeling to automate the evaluation and explanation of chatbot response inappropriateness. The framework first produces characterizations of context-aware DAs based on discourse analysis theory and real-world human-chatbot transcripts. It then automatically extracts features to identify the appropriateness level of a response and can explain the causes of the inappropriate response by examining the DA mismatch between the response and its conversational context. Using interview chatbots as a testbed, our framework achieves comparable classification accuracy with higher explainability and fewer computational resources than the deep learning baseline, making it the first step in utilizing DAs for chatbot response appropriateness evaluation and explanation.","PeriodicalId":127379,"journal":{"name":"Proceedings of the 5th International Conference on Conversational User Interfaces","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131279609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0