Skip to main content
SpringerLink
Log in

Saleshat: A LLM-Based Social Robot for Human-Like Sales Conversations

  • Conference paper
  • First Online:
Chatbot Research and Design (CONVERSATIONS 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14524))

Included in the following conference series:

Abstract

Large language models (LLMs) have generated excitement in many areas and may also make human-like conversations with social robots possible. Drawing from human-robot interaction literature and interviews, we developed Saleshat based on the commercial social robot Furhat and the large language model GPT-4. Saleshat emphasizes refined natural language processing and dynamic control of the robot’s physical appearance through the LLM. Responses from the LLM are processed sequentially, enabling the robot to react quickly. The results of our first formative evaluation with six users engaging in a sales conversation about Bluetooth speakers show that Saleshat can provide accurate and detailed responses, maintain a good conversation flow, and show dynamically controlled non-verbal cues. With our findings, we contribute to research on social robots and LLMs by providing design knowledge for LLM-based social robots and by uncovering the benefits and challenges of integrating LLMs into a social robot.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Nestlé to Use Humanoid Robot to Sell Nescafé in Japan (2014). https://www.nestle.com/media/news/nestle-humanoid-robot-nescafe-japan

  2. Al Moubayed, S., et al.: Furhat: a back-projected human-like robot head for multiparty human-machine interaction. In: Esposito, A., et al. (eds.) Cognitive Behavioural Systems, vol. 7403, pp. 114–130. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34584-5_9

  3. Bartneck, C., Forlizzi, J.: A design-centred framework for social human-robot interaction. In: RO-MAN 2004. 13th IEEE International Workshop on Robot and Human Interactive Communication (IEEE Catalog No.04TH8759), pp. 591–594. IEEE (2004). https://doi.org/10.1109/ROMAN.2004.1374827

  4. Breazeal, C.: Toward sociable robots. Robot. Autonom. Syst. 42(3–4), 167–175 (2003). https://doi.org/10.1016/S0921-8890(02)00373-1

  5. Breazeal, C., Scassellati, B.: A context-dependent attention system for a social robot. In: IJCAI International Joint Conference on Artificial Intelligence, vol. 2 (1999)

    Google Scholar 

  6. Brengman, M., De Gauquier, L., Willems, K., Vanderborght, B.: From stopping to shopping: an observational study comparing a humanoid service robot with a tablet service kiosk to attract and convert shoppers. J. Bus. Res. 134, 263–274 (2021). https://doi.org/10.1016/j.jbusres.2021.05.025

  7. Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020). https://doi.org/10.48550/ARXIV.2005.14165

  8. Bulmer, S., Elms, J., Moore, S.: Exploring the adoption of self-service checkouts and the associated social obligations of shopping practices. J. Retail. Consum. Serv. 42, 107–116 (2018)

    Article  Google Scholar 

  9. Cameron, G., et al.: Best practices for designing chatbots in mental healthcare - a case study on iHelpr (2018). https://doi.org/10.14236/ewic/HCI2018.129

  10. Castelo, N., et al.: Task-dependent algorithm aversion. J. Market. Res. 56, 809–825 (2019). https://doi.org/10.1177/0022243719851788

  11. Cherakara, N., et al.: FurChat: an embodied conversational agent using LLMs. arXiv preprint arXiv:2308.15214 (2023)

  12. Choi, S., Mattila, A.S., Bolton, L.E.: To err is human(-oid): how do consumers react to robot service failure and recovery? J. Serv. Res. 24(3), 354–371 (2021). https://doi.org/10.1177/1094670520978798

  13. Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022).

  14. Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper_files/paper/2017/file/d5e2c0adad503c91f91df240d0cd4e49-Paper.pdf

  15. Chuah, S.H.W., Yu, J.: The future of service: the power of emotion in human-robot interaction. J. Retail. Consum. Serv. 61, 102551 (2021). https://doi.org/10.1016/j.jretconser.2021.102551

  16. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/N19-1423

  17. Dietvorst, Berkeley J.., Simmons, Joseph P.., Massey, Cade: Overcoming Algorithm Aversion: People Will Use Imperfect Algorithms If They Can (Even Slightly) Modify Them. Management Science 64(3), 1155–1170 (2018). https://doi.org/10.1287/mnsc.2016.2643

    Article  Google Scholar 

  18. Driess, D., et al.: PaLM-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)

  19. Evers, K., Chen, S.: Effects of an automatic speech recognition system with peer feedback on pronunciation instruction for adults. Comput. Assist. Lang. Learn. 35, 1869–1889 (2022). https://doi.org/10.1080/09588221.2020.1839504

  20. Gilbert, S., Harvey, H., Melvin, T., Vollebregt, E., Wicks, P.: Large language model AI chatbots require approval as medical devices. Nat. Med. 29(10), 2396–2398 (2023). https://doi.org/10.1038/s41591-023-02412-6

  21. Henschel, A., Laban, G., Cross, E.S.: What makes a robot social? a review of social robots from science fiction to a home or hospital near you. Curr. Robot. Rep. 2(1), 9–19 (2021). https://doi.org/10.1007/s43154-020-00035-0

  22. Holthaus, P., Wachsmuth, S.: It was a pleasure meeting you: towards a holistic model of human-robot encounters. Int. J. Soc. Robot. 13, 1729–1745 (2021). https://doi.org/10.1007/s12369-021-00759-9

  23. Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55, 1–38 (2023). https://doi.org/10.1145/3571730

  24. Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020). https://doi.org/10.48550/ARXIV.2001.08361

  25. Lim, M.Y., et al.: Demonstration of a robo-barista for in the wild interactions (2022). https://doi.org/10.1109/HRI53351.2022.9889443

  26. Lu, L., Zhang, P., Zhang, T.C.: Leveraging “human-likeness" of robotic service at restaurants. Int. J. Hosp. Manag. 94, 102823 (2021). https://doi.org/10.1016/j.ijhm.2020.102823

  27. Mende, M.A., Fischer, M.H., Kühne, K.: The use of social robots and the uncanny valley phenomenon. In: Zhou, Y., Fischer, M.H. (eds.) AI Love You, pp. 41–73. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-19734-6_3

  28. Niemelä, M., Heikkilä, P., Lammi, H., Oksman, V.: A social robot in a shopping mall: studies on acceptance and stakeholder expectations. In: Korn, O. (ed.) Social Robots: Technological, Societal and Ethical Aspects of Human-Robot Interaction, pp. 119–144. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-17107-0_7

  29. OpenAI: Gpt-4 Technical Report (2023)

    Google Scholar 

  30. Pandey, A.K., Gelin, R.: A mass-produced sociable humanoid robot: pepper: the first machine of its kind. IEEE Robot. Automat. Magaz. 25(3), 40–48 (2018). https://doi.org/10.1109/MRA.2018.2833157

  31. Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., Yang, D.: Is chatGPT a general-purpose natural language processing task solver? In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023). https://openreview.net/forum?id=u03xn1COsO

  32. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https://api.semanticscholar.org/CorpusID:160025533

  33. Reich, T., et al.: How to overcome algorithm aversion: learning from mistakes. J. Consum. Psychol. 33 (2023). https://doi.org/10.1002/jcpy.1313

  34. Rindfleisch, A., Fukawa, N., Onzo, N.: Robots in retail: rolling out the whiz. AMS Rev. 12(3), 238–244 (2022). https://doi.org/10.1007/s13162-022-00240-4

  35. Ruoff, M., Gnewuch, U.: Designing multimodal bi &a systems for co-located team interactions (2021)

    Google Scholar 

  36. Shanahan, M.: Talking about large language models. arXiv preprint arXiv:2212.03551v5 (2022). https://doi.org/10.48550/ARXIV.2212.03551. Publisher: arXiv Version Number: 5

  37. Stark, C., et al.: Dobby: a conversational service robot driven by GPT-4. arXiv preprint arXiv:2310.06303v1 (2023). https://doi.org/10.48550/ARXIV.2310.06303

  38. Stock, R.M., Merkle, M.: A service robot acceptance model: User acceptance of humanoid robots during service encounters. In: 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), pp. 339–344. IEEE (2017). https://doi.org/10.1109/PERCOMW.2017.7917585

  39. Turner, J.J., Szymkowiak, A.: An analysis into early customer experiences of self-service checkouts: lessons for improved usability. Eng. Manag. Prod. Serv. 11(1), 36–50 (2019)

    Google Scholar 

  40. Van Pinxteren, M.M., Wetzels, R.W., Rüger, J., Pluymaekers, M., Wetzels, M.: Trust in humanoid robots: implications for services marketing. J. Serv. Market. 33(4), 507–518 (2019). https://doi.org/10.1108/JSM-01-2018-0045

  41. Vaswani, A., et al.: Attention is all you need (2017)

    Google Scholar 

  42. Wang, Y.J., Zhang, B., Chen, J., Sreenath, K.: Prompt a robot to walk with large language models. arXiv preprint arXiv:2309.09969 (2023)

  43. Wei, J., et al.: Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)

  44. Wilcock, G.: Generating more intelligent responses and explanations with conversational AI and knowledge graphs. In: The 36th Annual Conference of the Japanese Society for Artificial Intelligence (2022)

    Google Scholar 

  45. Zhong, Q., Ding, L., Liu, J., Du, B., Tao, D.: Can ChatGPT understand too? a comparative study on ChatGPT and fine-tuned BERT. arXiv preprint arXiv:2302.10198v2 (2023)

Download references

Author information

Authors and Affiliations

  1. Karlsruhe Institute of Technology, 76131, Karlsruhe, Germany

    Leon Hanschmann, Ulrich Gnewuch & Alexander Maedche

Authors
  1. Leon Hanschmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ulrich Gnewuch
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alexander Maedche
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Leon Hanschmann .

Editor information

Editors and Affiliations

  1. SINTEF, Oslo, Norway

    Asbjørn Følstad

  2. University of Amsterdam, Amsterdam, The Netherlands

    Theo Araujo

  3. CERTH-ITI, Thessaloniki, Greece

    Symeon Papadopoulos

  4. Department of Computer Science, Durham University, Durham, UK

    Effie L.-C. Law

  5. Design Informatics, University of Edinburgh, Edinburgh, UK

    Ewa Luger

  6. Centre for AI Research, University of Agder, Grimstad, Norway

    Morten Goodwin

  7. TH Lübeck – University of Applied Sciences, Lübeck, Germany

    Sebastian Hobert

  8. SINTEF & University of Oslo, Oslo, Norway

    Petter Bae Brandtzaeg

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hanschmann, L., Gnewuch, U., Maedche, A. (2024). Saleshat: A LLM-Based Social Robot for Human-Like Sales Conversations. In: Følstad, A., et al. Chatbot Research and Design. CONVERSATIONS 2023. Lecture Notes in Computer Science, vol 14524. Springer, Cham. https://doi.org/10.1007/978-3-031-54975-5_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-54975-5_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-54974-8

  • Online ISBN: 978-3-031-54975-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation