LLM Chatbots: Panacea or Pandora’s Box?

A special issue of Societies (ISSN 2075-4698).

Deadline for manuscript submissions: closed (1 November 2023) | Viewed by 13923

Special Issue Editors


E-Mail Website
Guest Editor
Utrecht University School of Governance, Utrecht University, 3511 ZC Utrecht, The Netherlands
Interests: fake news; reliable COVID-19 digital information; new media use: a generational approach; silver gaming; identification with digital images; visual ageism
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Media and Culture Studies, Utrecht University, 3512 EV Utrecht, The Netherlands
Interests: impact of datafication and algoritmization on culture and society

E-Mail Website
Guest Editor
School of Liberal Arts, Utrecht University, 3512 BR Utrecht, The Netherlands
Interests: applied data science; higher education research; human-centered artificial intelligence

Special Issue Information

ChatGPT, for a Special Issue we want to address the following question: ‘LLM chatbots: Panacea or Pandora's Box?’ How do you answer this question?

The question of whether LLM (Language Model-based) chatbots are a panacea or a Pandora's box is an intriguing one. Let us explore both perspectives:

Panacea:

  1. Enhanced Communication: LLM chatbots have the potential to revolutionize communication by providing quick and accurate responses across various domains. They can handle multiple languages, understand context, and offer personalized interactions.
  2. Efficiency and Convenience: Chatbots can handle numerous queries simultaneously, reducing response time and improving efficiency. They can automate repetitive tasks, freeing up human agents to focus on more complex and value-added activities.
  3. Scalability: LLM chatbots can scale effortlessly to handle large volumes of inquiries, ensuring consistent service quality. They are available 24/7, enabling businesses to provide round-the-clock support to their customers.
  4. Cost Savings: By automating customer interactions, organizations can potentially reduce costs associated with customer service and support functions. This is particularly beneficial for smaller businesses or those with limited resources.

Pandora's Box:

  1. Ethical Concerns: The capabilities of LLM chatbots raise ethical considerations regarding data privacy, transparency, and potential misuse. They require extensive data for training, which may lead to privacy concerns if not handled carefully.
  2. Bias and Discrimination: Chatbots can inadvertently perpetuate biases present in the data they are trained on, leading to discriminatory responses or actions. This can have negative social implications and contribute to inequality and injustice.
  3. Loss of Human Touch: While chatbots can provide efficient responses, they lack the human touch and empathy that some individuals desire. In emotionally charged situations, customers may prefer interacting with human agents who can better understand their needs.
  4. Technical Limitations: LLM chatbots are not infallible and can encounter difficulties when faced with complex or ambiguous queries. They may struggle to understand context, humor, or nuanced conversations, leading to frustrating user experiences.

Ultimately, whether LLM chatbots are a panacea or a Pandora's box depends on how they are developed, deployed, and regulated. By addressing ethical concerns, ensuring transparency, and focusing on continuous improvement, LLM chatbots can be valuable tools that enhance efficiency and customer experiences. However, caution must be exercised to prevent potential negative consequences and ensure a balanced approach to their implementation. 

26.05.2023 - Free Research Preview. ChatGPT may produce inaccurate information about people, places, or facts. ChatGPT May 24 Version

Dear Colleagues,

ChatGPT, a Large Language Model chatbot, generated the above answer when prompted to discuss whether LLM chatbots should be considered a Panacae or a Pandora’s Box. For our Special Issue, we are seeking contributions from human experts focusing on this topic. 

With their rapid integration and application across various sectors and in everyday life, LLM chatbots have triggered both optimistic and pessimistic responses. This Special Issue seeks to collect a selection of papers that critically explore the promise and peril of LLM chatbots from a variety of different fields, approaches and perspectives (e.g., governance, political economy, technology and usage). We welcome research articles, conceptual papers and reviews positioned within a specific field, such as education, science, journalism, medicine, technology, etc. Potential topics may include:

(1) The social, ethical, epistemological or environmental impact of using LLM chatbots such as ChatGPT  (Van Es et al, 2021), including its opportunities and threats in terms of its ability to extend human capabilities (Lawson, 2010).
(2) Ethical issues (Grunwald, 2014, Jonas, 1973), e.g., with regard to its training data (see https://www.washingtonpost.com/technology/interactive/2023/ai-chatbot-learning/) exploring issues of bias/stereotyping, content moderation policies.
(3) Accountability and regulation of generative AI.
(4) The characteristics of chatting with LLM chatbots (Champagne, 2023), e.g., anthropomorphism.
(5) The reliability of LLM chatbots’ answers (see Dumitru et al. (2022) and Loos & Ivan (2022) for discussions on accessible reliable digital information and Guo al.’s (2023) work on LLM chatbots versus human expertise) compared to those of other LLM chatbots, such as Bard, Perplexity AI and Neuroflash (see also https://aibusiness.com/nlp/7-language-models-you-need-to-know
(6) Media discourses around LLM chatbots, e.g., (Nguyen and Hekman, 2022) or their public perception (Brauner et al., 2023). 

References

Brauner, P., Hick, A., Philipsen, R., & Ziefle, M. (2023). What does the public think about artificial intelligence?—A criticality map to understand bias in the public perception of AI. Frontiers in Computer Science5, 19.

Champagne, M. (2023). Chatting with an AI, Chatting with a Human, What’s the Difference? Conference presentation. Conference: Philosophers’ Jam, Vancouver, Canada. file:///E:/Onderzoek/ChatGPT/MarcChampagneLangara2023.pdf

Dumitru, E.-A., Ivan, L., & Loos, E. (2022). A Generational Approach to Fight Fake News: In Search of Effective Media Literacy Training and Interventions. In Q. Gao & J. Zhou (Eds.), Human aspects of IT for the aged population, In International Conference on Human–computer Interaction, HCII 2022, LNCS series. Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-031-05581-2_22

Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., ... & Wu, Y. (2023). How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection. arXiv preprint arXiv:2301.07597.

Grunwald, A. (2014). Technology assessment for responsible innovation. Responsible innovation 1: Innovative solutions for global issues, 15-31.

Jonas, H. (1973). Technology and responsibility: Reflections on the new task of ethics. Social Research, 40, 31-54.

Lawson, C. L. I. V. E. (2010). Technology and the extension of human capabilities. Journal for the theory of social behaviour21, 8308.

Loos, E., & Ivan, L. (2022). Special Issue “Fighting Fake News: A Generational Approach.” Societies12(2), 57. https://www.mdpi.com/journal/societies/special_issues/fake_news

Nguyen, D., & Hekman, E. (2022). The news framing of artificial intelligence: a critical exploration of how media discourses make sense of automation. AI & Soc., DOI: 10.1007/s00146-022-01511-1

van Es, K., Schäfer, M. T., & Wieringa, M. (2021). Tool Criticism and the Computational Turn: A 'Methodological Moment' in Media and Communication Studies, 46-64 Nomos eLibrary, DOI: 10.5771/1615-634X-2021-1-46

Dr. Eugène Loos
Dr. Karin van Es
Dr. Rianne van Lambalgen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as conceptual papers are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a double-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Societies is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • large language models chatbots as innovative tool
  • ChatGPT
  • panacea
  • pandora’s box
  • opportunities
  • threats
  • social impact
  • anthropomorphism
  • human capability
  • ethics
  • accountability
  • regulation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Other

18 pages, 618 KiB  
Concept Paper
Using ChatGPT in Education: Human Reflection on ChatGPT’s Self-Reflection
by Eugène Loos, Johanna Gröpler and Marie-Louise Sophie Goudeau
Societies 2023, 13(8), 196; https://doi.org/10.3390/soc13080196 - 21 Aug 2023
Cited by 24 | Viewed by 12883
Abstract
ChatGPT is a fascinating AI text generator tool. It is a language model developed by OpenAI, a research and deployment company with the mission, according to OpenAI’s website: “to ensure that artificial general intelligence benefits all of humanity”. ChatGPT is able to generate [...] Read more.
ChatGPT is a fascinating AI text generator tool. It is a language model developed by OpenAI, a research and deployment company with the mission, according to OpenAI’s website: “to ensure that artificial general intelligence benefits all of humanity”. ChatGPT is able to generate human-like texts. But how does it work? What about the quality of the texts it provides? And is it capable of being self-reflective? Information sources must be efficient, effective and reliable in education, in order to enhance students’ learning process. For this reason, we started a dialogue with ChatGPT-3 while using, among others, a SWOT analysis it generated about its own functioning in an educational setting. This enabled us, as human authors, to analyze the extent to which this AI system is able to practice self-reflection. Finally, the paper sketches implications for education and future research. Full article
(This article belongs to the Special Issue LLM Chatbots: Panacea or Pandora’s Box?)
Back to TopTop