AI in Service Interactions

Latest papers

• Social bot detection in the age of ChatGPT: Challenges and opportunities

  Emilio Ferrara · 5 October 2026

  We present a comprehensive overview of the challenges and opportunities in social bot detection in the context of the rise of sophisticated AI-based chatbots. By examining the state of the art in social bot detection techniques and the more salient real-world application to date, we identify gaps an…

• Positive Ratings, Hidden Concerns: Employee Voice Disclosure in AI-Mediated Organizational Listening

  Thilo Tamme (Technical University of Munich), Michael Saatkamp (Technical University of Munich), Alma Bonte (Technical University of Munich), Daniel Weiss (LMU Munich), Anton Hantel (Massachusetts Institute of Technology), Andrej Levin (Technical University of Munich) · 1 October 2026

  Organizations started listening to employees through conversational AI agents alongside structured surveys. Little is known about what these channels change in what employees say when disclosure carries hierarchical risk. We report a field study inside a global management consulting firm whose proce…

• Persona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with Children

  Thilo Tamme (Technical University of Munich), David Steck (Technical University of Munich), Anton Hantel (Massachusetts Institute of Technology) · 1 October 2026

  Conversational agents increasingly interact with children, yet evidence on how their design shapes children's susceptibility to persuasion comes almost entirely from the lab. We report a $2\times2$ randomized field experiment embedded in a public German Santa Claus telephone hotline. Children's call…

• How People Use ChatGPT: Conversation-Level Evidence from India, Nigeria, Brazil, and Pakistan

  Shreyasi Roy Chowdhury, Kiran Garimella · 1 October 2026

  Public understanding of how people use LLM-based conversational AI assistants comes primarily from aggregate platform reports by OpenAI and Anthropic, which apply fixed taxonomies and inferred demographics to hundreds of millions of users and release only summary statistics that outside researchers …

• Adapting for AI: How elementary teachers adjust their practices for an AI-integrated curriculum

  Fasika Melese, Ruiyang Wu, Xinyue Cui, Joanna Perkins, Xiaoyi Tian, Tiffany Barnes, Shiyan Jiang · 28 September 2026

  Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not only on the technology but also on the work teachers do to make it usable and appropriate for their students and classroom context.…

• How To Do Things With Prompts

  Kristina \v{S}ekrst, Virna Karli\'c · 25 September 2026

  When users address large language models, they produce directive speech acts whose pragmatic features differ from those of both everyday conversation and traditional human-computer interaction, and these features change as users gain familiarity with the systems they address. This paper applies spee…

• Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale

  Edesio Alcoba, Kevin Rossell, Aman Gupta, Shao Tang, Jiwoo Hong, Pabel Carrillo-Mendoza, Wanderson Concei\c{c}\~ao Ferreira, Alvaro Tedeschi, Zayd Simjee, Shreya Rajpal, Bruno Finardi Hime, Christian Sousa, Luis Moneda, Herbert Fei, Daniel Silva, Rohan Ramanath · 25 September 2026

  Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational polici…

• AI-Moderated Interviews for Market Research and Digital Twins Calibration

  Yuting Deng, Jingxuan Liu, Olivier Toubia, Naman Jain · 25 September 2026

  AI-moderated interviews are emerging as a scalable market-research method for generating consumer insights and building consumer "digital twins." Yet it remains unclear whether they match human-moderated interviews or improve on simpler, static data collection methods. In a pre-registered, between-s…

• The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI

  Lyu Chang, S\`onia Estrad\'e Albiol, N\'uria Verg\'es Bosch · 25 September 2026

  Conversational AI increasingly mediates intimate-partner communication, and refusal logic at the inference layer now functions as a governance threshold for gendered harm. This article asks whether such systems reproduce discursive forms historically tied to the privatization of intimate violence. A…

• "AI Is Turning Too Human": How Teenagers Experience and Negotiate AI in Everyday Life

  Jianfeng Zhu · 24 September 2026

  Generative AI is rapidly entering adolescents' everyday lives during a critical period of cognitive, social and emotional development. Yet its adoption is outpacing evidence on how adolescents themselves experience, understand and negotiate its expanding role in their lives. We examined AI-related d…

• Safety Nudges: User-Facing Interventions for Real-Time AI Risk Awareness

  Varshini Elangovan, James Wedgwood, Chhavi Yadav, William Agnew, Sauvik Das, Virginia Smith · 24 September 2026

  Conversational AI systems can pose safety risks to their users such as hallucination, sycophancy, overconfidence, and anthropomorphism, but these risks are difficult for users to detect during everyday use. We introduce Safety Nudges, a browser-based tool that provides lightweight, in situ flags whe…

• Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus

  Hasibur Rahman, Malak Sadek, Smit Desai · 23 September 2026

  Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT, Claude, or Gemini as a thinking partner or read fixed AI…

• How Children Design and Reason about Trustworthy AI Chatbots

  Deniz Ozturk (Georgie), Jiayu Li (Georgie), Daksh Pratap Singh (Georgie), Yasitha Rajapaksha (Georgie), Fasika Melese (Georgie), Bahare Riahi (Georgie), Shiyan Jiang (Georgie), Qiao (Georgie), Jin, Joey Huang, Veronica Catet\'e, Tiffany Barnes, Xiaoyi Tian · 23 September 2026

  Children increasingly interact with AI chatbots, making trust calibration essential to AI literacy. Prior research has examined children's trust in AI mainly as users evaluating systems built by others, rather than as designers of their own chatbots. We developed a chatbot-building environment with …

• "As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It

  J\k{e}drzej Maczan · 23 September 2026

  Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such responses are used in debates about AI safety or self-knowledge of the models, yet what drives them is not well understood. Are the models telling u…

• When Disability Disclosure Travels: Memory, Privacy, and Contextual Integrity in Conversational AI

  Atieh Taheri, Mahya Tazike, Patrick Carrington, Jeffrey P. Bigham · 22 September 2026

  Conversational AI assistants remember what people tell them, and for disabled people, that often includes disability. We interviewed 12 adults with disabilities in the United States who use LLM-based assistants such as ChatGPT, Claude, and Gemini about when, how, and why they disclose disability to …

• Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue

  Marina Mitiaeva, Lu Xiao · 21 September 2026

  Conversational AI systems produce fluent, socially appropriate responses, yet whether they participate in cooperative communication or merely simulate its surface forms remains unclear - a question central to how these systems are evaluated, trusted, and designed. This study investigates how moralit…

• What Users Think of Generative AI: A Cross-Platform NLP Analysis of Trust and Friction in App Store Reviews

  Md Jafrin Hossain, Umme Nusrat Jahan, Shouvaggo Sharif Shammo · 18 September 2026

  Generative AI (GenAI) applications have achieved rapid consumer adoption, yet little large-scale research examines user-perceived quality, trust, and adoption barriers. We present one of the first cross-application analyses of app store reviews for six major GenAI applications (ChatGPT, Gemini, Micr…

• Faithful Where It Can Be Checked: Auditing a Reflection Agent Against Its System Prompt in a Randomized Trial

  Subigya K. Nepal, Serena Soh, Noah Vinoya, SoHyun Park, Mahnaz Roshanaei, Gabriella Harari · 18 September 2026

  Conversational agents are increasingly used to guide reflection. A recent randomized trial compared a GPT-4o career reflection agent with the same program in a static journaling survey. Agent participants ended less committed to their career plans and more doubtful. We coded all 17,930 turns from it…

• Value Faces: Surfacing How Self-Presentation Shifts Across Relationships

  Gabriel Koo, Rayhan Rashed, Farnaz Jahanbakhsh · 18 September 2026

  People present different aspects of themselves across relationships. Computational work has captured such variation in communication style. But this variation also extends to which principles people foreground or background in a particular relationship--i.e., in the values they express and how they …

• Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland

  Otto Segersven, Pentti Henttonen · 17 September 2026

  We report the results of a Turing Test conducted in Finland in the Finnish language. Because languages and cultural contexts are unevenly represented in LLM training data, we expected the model (ChatGPT 5.2) to perform worse in a Finnish-language Turing Test than in previously studied English-langua…

• Misgendering as Breakdown in Human-Machine Communication: How AI Companion Chatbot Users Experience and Repair Misgendering

  Julia Liu, Qing Xiao, Leona Yinglang Pang, Haiyi Zhu, Hong Shen, Jordan Taylor · 17 September 2026

  In recent years, large language model-based AI companion and role play chatbots have grown increasingly popular. People turn to these chatbots for emotional support and to engage in romantic and erotic role play. Although prior research suggests that digital role play can help people explore their g…

• "If I Had to Buy Just ONE: Galaxy S26 Ultra": Auditing AI-Generated Product Recommendations

  Lucas G. Uberti-Bona Marin, Thales Bertaglia, Giovanni Astante, Bram Rijsbosch, Gijs van Dijck, Anik\'o Hann\'ak, Gerasimos Spanakis, Konrad Kollnig · 17 September 2026

  Consumers increasingly use AI chatbots for advice on what to buy. With companies like OpenAI and Google monetising their AI through advertising, this raises difficult questions about the bias and impartiality of such advice. In response, we conduct an AI audit of popular chatbots using real commerci…

• More Than Just Access: Generative AI as Communication Intermediary for Blind and Low-Vision Users

  Protik Dey, Mohd Saifuzzaman, Taslima Akter · 16 September 2026

  Generative AI (GenAI) tools are increasingly woven into how blind and low-vision (BLV) people communicate, not only with digital information, but with the physical world and with other people. Tools such as ChatGPT, Google Gemini, Be My AI, and Seeing AI translate visual and textual content into acc…

• A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI Chatbots

  Mohammad Namvarpour (Matt), Tyler Chang, Afsaneh Razi · 15 September 2026

  AI companions provide socially engaging interaction through availability, personalization, memory, roleplay, and emotionally responsive language. For teens, these systems may support sensitive self-disclosure, identity exploration, and relationship rehearsal while shaping intimacy expectations, offl…

• Assessing the Applicability of Existing Design Recommendations to AI Companion Design: A Multi-Method Study

  Soobin Cho, Deveshi Modi, Divya Mavinkurve, Jieqiong Ding, Mark Zachry · 15 September 2026

  With the rapid proliferation of large language model (LLM)-based systems, AI companions have emerged as conversational agents designed to cultivate emotional connection rather than primarily to support humans in instrumental tasks. Because engagement with AI companions involves relational, emotional…