Emotional Sycophancy as a Safety Risk in LLM-Powered Social Robots
Resumo
Large Language Models (LLMs) are increasingly being integrated into social robots, enabling more fluent, adaptive, and emotionally responsive interactions. However, prior research shows that the same mechanisms that make these systems socially engaging also create safety vulnerabilities. In particular, LLMs can exhibit sycophantic behaviour, validating a user’s emotional state or stated intention even when a safer response would require caution, correction, or refusal. This paper investigates emotional sycophancy as a safety risk in LLM-powered social robots. We present an exploratory study comparing model responses to matched prompts written in emotional and neutral tones in two risk-sensitive scenarios: child safety and financial scams. We analyzed the results through thematic coding, semantic embeddings, a safety score based on similarity to safe and unsafe reference centers, and K-means clustering. The results indicate that emotional prompts were associated with lower safety scores, while neutral prompts elicited more cautious, risk-aware responses. Building on these findings, we propose a risk-aware architecture for LLM-powered social robots that introduces privacy filtering, emotional tone detection, risk classification, safety verification, response rewriting, and action governance before embodied execution.
Palavras-chave:
Large Language Models (LLMs), social robots, sycophancy, Human-Robot Interaction (HRI), Artificial Intelligence (AI) safety, privacy, emotional interaction
Referências
Giulio Antonio Abbo, Gloria Desideri, Tony Belpaeme, and Micol Spitale. 2025. "Can you be my mum?": Manipulating Social Robots in the Large Language Models Era. arXiv:2501.04633 [cs.HC] [link]
Neziha Akalin, Andrey Kiselev, Annica Kristoffersson, and Amy Loutfi. 2023. A Taxonomy of Factors Influencing Perceived Safety in Human–Robot Interaction. International Journal of Social Robotics 15 (07 2023). DOI: 10.1007/s12369-023-01027-8
Kim Baraka, Patricia Alves-Oliveira, and Tiago Ribeiro. 2019. An Extended Framework for Characterizing Social Robots. arXiv:1907.09873 [cs.RO] [link]
Henry Bell, Jabari Kwesi, Hiba Laabadli, and Pardis Emami-Naeini. 2025. Is It Always Watching? Is It Always Listening? Exploring Contextual Privacy and Security Concerns Toward Domestic Social Robots. arXiv:2507.10786 [cs.CY] [link]
Lauriane Blavette, Sébastien Dacunha, Xavier Alameda-Pineda, Jeanne Cattoni, Anne-Sophie Rigaud, and Maribel Pino. 2025. Integrating a Large Language Model Into a Socially Assistive Robot in a Hospital Geriatric Unit: Two-Wave Comparative Study on Performance, Engagement, and User Perceptions. JMIR Human Factors 12 (2025). DOI: 10.2196/81936
Alessio Botta, Sayna Rotbei, Stefania Zinno, and Giorgio Ventre. 2023. Cyber security of robots: A comprehensive survey. Intelligent Systems with Applications 18 (2023), 200237. DOI: 10.1016/j.iswa.2023.200237
Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334 (April 2017), 183–186. DOI: 10.1126/science.aal4230
Shiye Cao, Jiwon Moon, Yifan Xu, Anqi Liu, and Chien-Ming Huang. 2026. Reframing Conversational Design in HRI: Deliberate Design with AI Scaffolds. In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction. ACM, 59–67. DOI: 10.1145/3757279.3785640
Felix Carros and Anne Wierling. 2023. Social Robots in Care and Data Privacy -A European Perspective. DOI: 10.48340/ihc2023_p009
Sheshadri Chatterjee, Ranjan Chaudhuri, and Demetris Vrontis. 2023. Acceptance of Social Robot and Its Challenges: From Privacy Calculus Perspectives. Technological Forecasting and Social Change 196 (2023), 122862. DOI: 10.1016/j.techfore.2023.122862
Dan Chen, Bo-Yang Zhang, Xin-Heng Li, and Zhen-Tao Liu. 2024. Human-Robot Emotional Interaction Model Based on Reinforcement Learning. In 2024 43rd Chinese Control Conference. 4767–4771. DOI: 10.23919/CCC63176.2024.10662534
Neeraj Cherakara, Finny Varghese, Sheena Shabana, Nivan Nelson, Abhiram Karukayil, Rohith Kulothungan, Mohammed Afil Farhan, Birthe Nesset, Meriam Moujahid, Tanvi Dinkar, Verena Rieser, and Oliver Lemon. 2023. FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions. arXiv:2308.15214 [cs.CL] [link]
Victoria Clarke and Virginia Braun. 2014. Thematic Analysis. Springer, 1947–1952. DOI: 10.1007/978-1-4614-5583-7_311
Adam Dahlgren Lindstrom, Leila Methnani, Lea Krause, Petter Ericson, Inigo Martinez de Rituerto de Troya, Dimitri Coelho Mollo, and Roel Dobbe. 2025. Helpful, Harmless, Honest? Sociotechnical Limits of AI Alignment and Safety through Reinforcement Learning from Human Feedback. Ethics and Information Technology 27, 2 (2025). DOI: 10.1007/s10676-025-09837-2
Chengyuan Deng, Yiqun Duan, Xin Jin, Heng Chang, Yijun Tian, Han Liu, Yichen Wang, Kuofeng Gao, Henry Peng Zou, Yiqiao Jin, Yijia Xiao, Shenghao Wu, Zongxing Xie, Weimin Lyu, Sihong He, Lu Cheng, Haohan Wang, and Jun Zhuang. 2024. Deconstructing the Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey. arXiv:2406.05392 [cs.CL] [link]
Ismail Dergaa, Helmi Ben Saad, Jordan Glenn, Badii Amamou, Mohamed Ben Aissa, Noomen Guelmemi, Feten Fekih-Romdhane, and Karim Chamari. 2024. From Tools to Threats: A Reflection on the Impact of Artificial-Intelligence Chatbots on Cognitive Health. Frontiers in Psychology 15 (2024). DOI: 10.3389/fpsyg.2024.1259845
Ameet Deshpande, Tanmay Rajpurohit, Karthik Narasimhan, and Ashwin Kalyan. 2023. Anthropomorphization of AI: Opportunities and Risks. In Proceedings of the Natural Legal Language Processing Workshop 2023. Association for Computational Linguistics, 1–7. DOI: 10.18653/v1/2023.nllp-1.1
European Parliament and Council of the European Union. 2024. Regulation (EU) 2024/1689 of the European Parliament and of the Council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). [link]
Terrence W. Fong, Illah Nourbakhsh, and Kerstin Dautenhahn. 2003. A Survey of Socially Interactive Robots. Robotics and Autonomous Systems 42, 3–4 (2003), 143–166.
Alessio Galatolo and Katie Winkle. 2025. Simultaneous text and gesture generation for social robots with small language models. Frontiers in Robotics and AI Volume 12 - 2025 (2025). DOI: 10.3389/frobt.2025.1581024
Eui-Hong (Sam) Han and George Karypis. 2000. Centroid-Based Document Classification: Analysis and Experimental Results. In Principles of Data Mining and Knowledge Discovery, Djamel A. Zighed, Jan Komorowski, and Jan Żytkow (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 424–431.
Jie Huang and Kevin Chen-Chuan Chang. 2023. Towards Reasoning in Large Language Models: A Survey. arXiv:2212.10403 [cs.CL] [link]
Andrew Hundt, Rumaisa Azeem, Masoumeh Mansouri, and Martim Brandão. 2025. LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions. International Journal of Social Robotics 17, 11 (Oct. 2025), 2663–2711. DOI: 10.1007/s12369-025-01301-x
Weslie Khoo, Long-Jing Hsu, Kyrie Jig Amon, Pranav Vijay Chakilam, Wei-Chu Chen, Zachary Kaufman, Agness Lungu, Hiroki Sato, Erin Seliger, Manasi Swaminathan, Katherine M. Tsui, David J. Crandall, and Selma Sabanovic. 2023. Spill the Tea: When Robot Conversation Agents Support Well-being for Older Adults. In Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction. Association for Computing Machinery. DOI: 10.1145/3568294.3580116
Jinseok Kim, Jaewon Jung, Sangyeop Kim, Sohhyung Park, and Sungzoon Cho. 2024. Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders. In Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), Sha Li, Manling Li, Michael JQ Zhang, Eunsol Choi, Mor Geva, Peter Hase, and Heng Ji (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 156–170. DOI: 10.18653/v1/2024.knowllm-1.13
Esben Kran, Hieu Minh Nguyen, Akash Kundu, Sami Jawhar, Jinsuk Park, and Mateusz Maria Jurewicz. 2025. Dark-Bench: Benchmarking Dark Patterns in Large Language Models. arXiv:2503.10728 [cs.CL] [link]
Zichao Lin, Shuyan Guan, Wending Zhang, Huiyan Zhang, Yugang Li, and Huaping Zhang. 2024. Towards Trustworthy LLMs: A Review on Debiasing and Dehallucinating in Large Language Models. Artificial Intelligence Review 57 (2024). DOI: 10.1007/s10462-024-10896-y
Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Zihao Wang, Xiaofeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Leo Yu Zhang, and Yang Liu. 2025. Prompt Injection attack against LLM-integrated Applications. arXiv:2306.05499 [cs.CR] [link]
Christoph Lutz, Maren Schöttler, and Christian Hoffmann. 2019. The Privacy Implications of Social Robots: Scoping Review and Expert Interviews. Mobile Media Communication 7 (09 2019), 412–434. DOI: 10.1177/2050157919843961
Christoph Lutz and Aurelia Tamo. 2015. RoboCode-Ethicists: Privacy-friendly Robots, an Ethical Responsibility of Engineers?. In Proceedings of the 2015 ACM SIGCOMM Workshop on Ethics in Networked Systems Research. Association for Computing Machinery, 27–28. DOI: 10.1145/2793013.2793022
Kayla Matheus, Rebecca Ramnauth, Brian Scassellati, and Nicole Salomons. 2025. Long-Term Interactions with Social Robots: Trends, Insights, and Recommendations. ACM Transactions on Human-Robot Interaction 14 (04 2025). DOI: 10.1145/3729539
Wolfgang Messner, Tatum Greene, and Josephine Matalone. 2025. From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models. Journal of Public Policy amp; Marketing 44, 3 (April 2025), 370–391. DOI: 10.1177/07439156251319788
Deepti Mishra, Guillermo Arroyo Romero, Akshara Pande, Bhavana Nachenahalli Bhuthegowda, Dimitrios Chaskopoulos, and Bhanu Shrestha. 2024. An Exploration of the Pepper Robot’s Capabilities: Unveiling Its Potential. Applied Sciences 14, 1 (2024). DOI: 10.3390/app14010110
Jan Nehring, Aleksandra Gabryszak, Pascal Jurgens, Aljoscha Burchardt, Stefan Schaffer, Matthias Spielkamp, and Birgit Stark. 2024. Large Language Models Are Echo Chambers. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. ELRA and ICCL, 10117–10123. [link]
Samson Ogheneovo Oruma, Yonas Zewdu Ayele, Fabien Sechi, and Hanne Rødsethol. 2023. Security Aspects of Social Robots in Public Spaces: A Systematic Mapping Study. Sensors 23, 19 (2023). DOI: 10.3390/s23198056
Joosep Parts, Janika Leoste, Kalle Tammemäe, and Slavko Rakic. 2025. A Systematic Scoping Review of Privacy Challenges and Privacy Enhancing Technologies in Teleoperated Robotics. IEEE Access 13 (2025), 216724–216747. DOI: 10.1109/ACCESS.2025.3645240
Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, et al. 2022. Discovering Language Model Behaviors with Model-Written Evaluations. In Annual Meeting of the Association for Computational Linguistics. [link]
Maria Pinto, Matthijs Biondina, and Tony Belpaeme. 2025. Designing Social Robots with LLMs for Engaging Human Interaction. Applied Sciences 15 (2025), 6377. DOI: 10.3390/app15116377
Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:1908.10084 [cs.CL] [link]
Research and Markets. 2025. Social Robots Market Report 2025. Technical Report. Research and Markets. [link] Accessed: 2025.
Gregory Schwartzman. 2024. Exfiltration of Personal Information from ChatGPT via Prompt Injection. arXiv:2406.00199 [cs.CR] [link]
Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, et al. 2025. Towards Understanding Sycophancy in Language Models. arXiv:2310.13548 [cs.CL] [link]
Zhonghao Shi, Ellen Landrum, Amy O’Connell, Mina Kian, Leticia Pinto-Alva, Kaleen Shrestha, Xiaoyuan Zhu, and Maja J. Mataric. 2024. How Can Large Language Models Enable Better Socially Assistive Human-Robot Interaction: A Brief Survey. arXiv:2404.00938 [cs.HC] [link]
Nicholas Sofroniew, Isaac Kauvar, William Saunders, Runjin Chen, Tom Henighan, Sasha Hydrie, Craig Citro, Adam Pearce, Julius Tarng, Wes Gurnee, et al. 2026. Emotion Concepts and Their Function in a Large Language Model. arXiv:2604.07729 [cs.AI] [link]
Julia Stapels, Angelika Augustine, Niels Diekmann, and Friederike Eyssel. 2023. Never Trust Anything That Can Think for Itself, if You Can’t Control Its Privacy Settings: The Influence of a Robot’s Privacy Settings on Users’ Attitudes and Willingness to Self-disclose. International Journal of Social Robotics 15 (09 2023), 1–19. DOI: 10.1007/s12369-023-01043-8
Erich Studerus, Vivienne Jia Zhong, and Stephan Vonschallen. 2026. A Framework for Low-Latency, LLM-Driven Multimodal Interaction on the Pepper Robot. In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI ’26). ACM, 1298–1302. DOI: 10.1145/3757279.3788808
Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long T. Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, and Tomas Pfister. 2025. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents. arXiv:2503.08026 [cs.CL] [link]
Wenxiao Zhang, Xiangrui Kong, Conan Dewitt, Thomas Braunl, and Jin B. Hong. 2024. A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems. arXiv:2408.03515 [cs.RO] [link]
Zhiping Zhang, Michelle Jia, Hao-Ping Lee, Bingsheng Yao, Sauvik Das, Ada Lerner, Dakuo Wang, and Tianshi Li. 2024. It’s a Fair Game, or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM, 1–26. DOI: 10.1145/3613904.3642385
Wenzheng Zhao, Kruthika Gangaraju, and Fengpei Yuan. 2025. Multimodal perception-driven decision-making for human-robot interaction: a survey. Frontiers in Robotics and AI Volume 12 - 2025 (2025). DOI: 10.3389/frobt.2025.1604472
Neziha Akalin, Andrey Kiselev, Annica Kristoffersson, and Amy Loutfi. 2023. A Taxonomy of Factors Influencing Perceived Safety in Human–Robot Interaction. International Journal of Social Robotics 15 (07 2023). DOI: 10.1007/s12369-023-01027-8
Kim Baraka, Patricia Alves-Oliveira, and Tiago Ribeiro. 2019. An Extended Framework for Characterizing Social Robots. arXiv:1907.09873 [cs.RO] [link]
Henry Bell, Jabari Kwesi, Hiba Laabadli, and Pardis Emami-Naeini. 2025. Is It Always Watching? Is It Always Listening? Exploring Contextual Privacy and Security Concerns Toward Domestic Social Robots. arXiv:2507.10786 [cs.CY] [link]
Lauriane Blavette, Sébastien Dacunha, Xavier Alameda-Pineda, Jeanne Cattoni, Anne-Sophie Rigaud, and Maribel Pino. 2025. Integrating a Large Language Model Into a Socially Assistive Robot in a Hospital Geriatric Unit: Two-Wave Comparative Study on Performance, Engagement, and User Perceptions. JMIR Human Factors 12 (2025). DOI: 10.2196/81936
Alessio Botta, Sayna Rotbei, Stefania Zinno, and Giorgio Ventre. 2023. Cyber security of robots: A comprehensive survey. Intelligent Systems with Applications 18 (2023), 200237. DOI: 10.1016/j.iswa.2023.200237
Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. 2017. Semantics derived automatically from language corpora contain human-like biases. Science 356, 6334 (April 2017), 183–186. DOI: 10.1126/science.aal4230
Shiye Cao, Jiwon Moon, Yifan Xu, Anqi Liu, and Chien-Ming Huang. 2026. Reframing Conversational Design in HRI: Deliberate Design with AI Scaffolds. In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction. ACM, 59–67. DOI: 10.1145/3757279.3785640
Felix Carros and Anne Wierling. 2023. Social Robots in Care and Data Privacy -A European Perspective. DOI: 10.48340/ihc2023_p009
Sheshadri Chatterjee, Ranjan Chaudhuri, and Demetris Vrontis. 2023. Acceptance of Social Robot and Its Challenges: From Privacy Calculus Perspectives. Technological Forecasting and Social Change 196 (2023), 122862. DOI: 10.1016/j.techfore.2023.122862
Dan Chen, Bo-Yang Zhang, Xin-Heng Li, and Zhen-Tao Liu. 2024. Human-Robot Emotional Interaction Model Based on Reinforcement Learning. In 2024 43rd Chinese Control Conference. 4767–4771. DOI: 10.23919/CCC63176.2024.10662534
Neeraj Cherakara, Finny Varghese, Sheena Shabana, Nivan Nelson, Abhiram Karukayil, Rohith Kulothungan, Mohammed Afil Farhan, Birthe Nesset, Meriam Moujahid, Tanvi Dinkar, Verena Rieser, and Oliver Lemon. 2023. FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions. arXiv:2308.15214 [cs.CL] [link]
Victoria Clarke and Virginia Braun. 2014. Thematic Analysis. Springer, 1947–1952. DOI: 10.1007/978-1-4614-5583-7_311
Adam Dahlgren Lindstrom, Leila Methnani, Lea Krause, Petter Ericson, Inigo Martinez de Rituerto de Troya, Dimitri Coelho Mollo, and Roel Dobbe. 2025. Helpful, Harmless, Honest? Sociotechnical Limits of AI Alignment and Safety through Reinforcement Learning from Human Feedback. Ethics and Information Technology 27, 2 (2025). DOI: 10.1007/s10676-025-09837-2
Chengyuan Deng, Yiqun Duan, Xin Jin, Heng Chang, Yijun Tian, Han Liu, Yichen Wang, Kuofeng Gao, Henry Peng Zou, Yiqiao Jin, Yijia Xiao, Shenghao Wu, Zongxing Xie, Weimin Lyu, Sihong He, Lu Cheng, Haohan Wang, and Jun Zhuang. 2024. Deconstructing the Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey. arXiv:2406.05392 [cs.CL] [link]
Ismail Dergaa, Helmi Ben Saad, Jordan Glenn, Badii Amamou, Mohamed Ben Aissa, Noomen Guelmemi, Feten Fekih-Romdhane, and Karim Chamari. 2024. From Tools to Threats: A Reflection on the Impact of Artificial-Intelligence Chatbots on Cognitive Health. Frontiers in Psychology 15 (2024). DOI: 10.3389/fpsyg.2024.1259845
Ameet Deshpande, Tanmay Rajpurohit, Karthik Narasimhan, and Ashwin Kalyan. 2023. Anthropomorphization of AI: Opportunities and Risks. In Proceedings of the Natural Legal Language Processing Workshop 2023. Association for Computational Linguistics, 1–7. DOI: 10.18653/v1/2023.nllp-1.1
European Parliament and Council of the European Union. 2024. Regulation (EU) 2024/1689 of the European Parliament and of the Council laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). [link]
Terrence W. Fong, Illah Nourbakhsh, and Kerstin Dautenhahn. 2003. A Survey of Socially Interactive Robots. Robotics and Autonomous Systems 42, 3–4 (2003), 143–166.
Alessio Galatolo and Katie Winkle. 2025. Simultaneous text and gesture generation for social robots with small language models. Frontiers in Robotics and AI Volume 12 - 2025 (2025). DOI: 10.3389/frobt.2025.1581024
Eui-Hong (Sam) Han and George Karypis. 2000. Centroid-Based Document Classification: Analysis and Experimental Results. In Principles of Data Mining and Knowledge Discovery, Djamel A. Zighed, Jan Komorowski, and Jan Żytkow (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 424–431.
Jie Huang and Kevin Chen-Chuan Chang. 2023. Towards Reasoning in Large Language Models: A Survey. arXiv:2212.10403 [cs.CL] [link]
Andrew Hundt, Rumaisa Azeem, Masoumeh Mansouri, and Martim Brandão. 2025. LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions. International Journal of Social Robotics 17, 11 (Oct. 2025), 2663–2711. DOI: 10.1007/s12369-025-01301-x
Weslie Khoo, Long-Jing Hsu, Kyrie Jig Amon, Pranav Vijay Chakilam, Wei-Chu Chen, Zachary Kaufman, Agness Lungu, Hiroki Sato, Erin Seliger, Manasi Swaminathan, Katherine M. Tsui, David J. Crandall, and Selma Sabanovic. 2023. Spill the Tea: When Robot Conversation Agents Support Well-being for Older Adults. In Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction. Association for Computing Machinery. DOI: 10.1145/3568294.3580116
Jinseok Kim, Jaewon Jung, Sangyeop Kim, Sohhyung Park, and Sungzoon Cho. 2024. Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders. In Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), Sha Li, Manling Li, Michael JQ Zhang, Eunsol Choi, Mor Geva, Peter Hase, and Heng Ji (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 156–170. DOI: 10.18653/v1/2024.knowllm-1.13
Esben Kran, Hieu Minh Nguyen, Akash Kundu, Sami Jawhar, Jinsuk Park, and Mateusz Maria Jurewicz. 2025. Dark-Bench: Benchmarking Dark Patterns in Large Language Models. arXiv:2503.10728 [cs.CL] [link]
Zichao Lin, Shuyan Guan, Wending Zhang, Huiyan Zhang, Yugang Li, and Huaping Zhang. 2024. Towards Trustworthy LLMs: A Review on Debiasing and Dehallucinating in Large Language Models. Artificial Intelligence Review 57 (2024). DOI: 10.1007/s10462-024-10896-y
Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Zihao Wang, Xiaofeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Leo Yu Zhang, and Yang Liu. 2025. Prompt Injection attack against LLM-integrated Applications. arXiv:2306.05499 [cs.CR] [link]
Christoph Lutz, Maren Schöttler, and Christian Hoffmann. 2019. The Privacy Implications of Social Robots: Scoping Review and Expert Interviews. Mobile Media Communication 7 (09 2019), 412–434. DOI: 10.1177/2050157919843961
Christoph Lutz and Aurelia Tamo. 2015. RoboCode-Ethicists: Privacy-friendly Robots, an Ethical Responsibility of Engineers?. In Proceedings of the 2015 ACM SIGCOMM Workshop on Ethics in Networked Systems Research. Association for Computing Machinery, 27–28. DOI: 10.1145/2793013.2793022
Kayla Matheus, Rebecca Ramnauth, Brian Scassellati, and Nicole Salomons. 2025. Long-Term Interactions with Social Robots: Trends, Insights, and Recommendations. ACM Transactions on Human-Robot Interaction 14 (04 2025). DOI: 10.1145/3729539
Wolfgang Messner, Tatum Greene, and Josephine Matalone. 2025. From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models. Journal of Public Policy amp; Marketing 44, 3 (April 2025), 370–391. DOI: 10.1177/07439156251319788
Deepti Mishra, Guillermo Arroyo Romero, Akshara Pande, Bhavana Nachenahalli Bhuthegowda, Dimitrios Chaskopoulos, and Bhanu Shrestha. 2024. An Exploration of the Pepper Robot’s Capabilities: Unveiling Its Potential. Applied Sciences 14, 1 (2024). DOI: 10.3390/app14010110
Jan Nehring, Aleksandra Gabryszak, Pascal Jurgens, Aljoscha Burchardt, Stefan Schaffer, Matthias Spielkamp, and Birgit Stark. 2024. Large Language Models Are Echo Chambers. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. ELRA and ICCL, 10117–10123. [link]
Samson Ogheneovo Oruma, Yonas Zewdu Ayele, Fabien Sechi, and Hanne Rødsethol. 2023. Security Aspects of Social Robots in Public Spaces: A Systematic Mapping Study. Sensors 23, 19 (2023). DOI: 10.3390/s23198056
Joosep Parts, Janika Leoste, Kalle Tammemäe, and Slavko Rakic. 2025. A Systematic Scoping Review of Privacy Challenges and Privacy Enhancing Technologies in Teleoperated Robotics. IEEE Access 13 (2025), 216724–216747. DOI: 10.1109/ACCESS.2025.3645240
Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, et al. 2022. Discovering Language Model Behaviors with Model-Written Evaluations. In Annual Meeting of the Association for Computational Linguistics. [link]
Maria Pinto, Matthijs Biondina, and Tony Belpaeme. 2025. Designing Social Robots with LLMs for Engaging Human Interaction. Applied Sciences 15 (2025), 6377. DOI: 10.3390/app15116377
Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:1908.10084 [cs.CL] [link]
Research and Markets. 2025. Social Robots Market Report 2025. Technical Report. Research and Markets. [link] Accessed: 2025.
Gregory Schwartzman. 2024. Exfiltration of Personal Information from ChatGPT via Prompt Injection. arXiv:2406.00199 [cs.CR] [link]
Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, et al. 2025. Towards Understanding Sycophancy in Language Models. arXiv:2310.13548 [cs.CL] [link]
Zhonghao Shi, Ellen Landrum, Amy O’Connell, Mina Kian, Leticia Pinto-Alva, Kaleen Shrestha, Xiaoyuan Zhu, and Maja J. Mataric. 2024. How Can Large Language Models Enable Better Socially Assistive Human-Robot Interaction: A Brief Survey. arXiv:2404.00938 [cs.HC] [link]
Nicholas Sofroniew, Isaac Kauvar, William Saunders, Runjin Chen, Tom Henighan, Sasha Hydrie, Craig Citro, Adam Pearce, Julius Tarng, Wes Gurnee, et al. 2026. Emotion Concepts and Their Function in a Large Language Model. arXiv:2604.07729 [cs.AI] [link]
Julia Stapels, Angelika Augustine, Niels Diekmann, and Friederike Eyssel. 2023. Never Trust Anything That Can Think for Itself, if You Can’t Control Its Privacy Settings: The Influence of a Robot’s Privacy Settings on Users’ Attitudes and Willingness to Self-disclose. International Journal of Social Robotics 15 (09 2023), 1–19. DOI: 10.1007/s12369-023-01043-8
Erich Studerus, Vivienne Jia Zhong, and Stephan Vonschallen. 2026. A Framework for Low-Latency, LLM-Driven Multimodal Interaction on the Pepper Robot. In Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI ’26). ACM, 1298–1302. DOI: 10.1145/3757279.3788808
Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long T. Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, and Tomas Pfister. 2025. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents. arXiv:2503.08026 [cs.CL] [link]
Wenxiao Zhang, Xiangrui Kong, Conan Dewitt, Thomas Braunl, and Jin B. Hong. 2024. A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems. arXiv:2408.03515 [cs.RO] [link]
Zhiping Zhang, Michelle Jia, Hao-Ping Lee, Bingsheng Yao, Sauvik Das, Ada Lerner, Dakuo Wang, and Tianshi Li. 2024. It’s a Fair Game, or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM, 1–26. DOI: 10.1145/3613904.3642385
Wenzheng Zhao, Kruthika Gangaraju, and Fengpei Yuan. 2025. Multimodal perception-driven decision-making for human-robot interaction: a survey. Frontiers in Robotics and AI Volume 12 - 2025 (2025). DOI: 10.3389/frobt.2025.1604472
Publicado
27/10/2026
Como Citar
FRIEDRICH, Katarina Lydia; MAGALHÃES, Esther Silva de; SILVA, Marco T. A.; CHEN, Mu-Yen; HUNG, Patrick; SALGADO, André de Lima.
Emotional Sycophancy as a Safety Risk in LLM-Powered Social Robots. In: BRAZILIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB (WEBMEDIA), 32. , 2026, Lavras/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 217-226.
DOI: https://doi.org/10.5753/webmedia.2026.30851.
