Abstract
There has been a huge uproar about ChatGPT in recent times. There are widespread fears that generative models such as ChatGPT will affect employability and bring humanity closer towards singularity. In this paper, we assessed the capabilities and limitations of ChatGPT empirically. We subjected ChatGPT to a series of questions with different levels of lexical and syntactic language complexity and manually scored the responses. We measured the lexical and syntactic complexity of the questions using text analytics techniques. The analysis of the responses showed ChatGPT as a highly capable language model, with certain limitations. ChatGPT showed an increased likelihood of generating an inaccurate response with increase in syntactic language complexity. Though there have been sporadic efforts and reports about ChatGPT’s limitations, this paper presents a pioneering structured approach towards assessing ChatGPT’s language capabilities. This study takes a small, yet important step in research towards assessing language models. It opens avenues for future research towards strengthening the generator model and developing the discriminator dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Turing, A.M.: Intelligent machinery, a heretical theory*. Philos. Math. 4, 256–260 (1996). https://doi.org/10.1093/philmat/4.3.256
Cadwalladr, C.: Are the robots about to rise? Google’s new director of engineering thinks so…, (2014). https://www.theguardian.com/technology/2014/feb/22/robots-google-ray-kurzweil-terminator-singularity-artificial-intelligence
Joy, B.: Why the future doesn’t need us (2000). http://www.wired.com/wired/archive/8.04/joy.%0Ahtml
Eden, A.H., Steinhart, E., Pearce, D., Moor, J.H.: Singularity hypotheses: a scientific and philosophical assessment. Front. Collect. 1–13 (2012). https://doi.org/10.1007/978-3-642-32560-1
Lee, L.-H., et al.: All one needs to know about Metaverse: a complete survey on technological singularity, virtual ecosystem, and research agenda. J. Latex Class Files. 14, 1–66 (2021). https://doi.org/10.48550/arXiv.2110.05352
Trueman, C.: Tech layoffs in 2023: A timeline (2023). https://www.computerworld.com/article/3685936/tech-layoffs-in-2023-a-timeline.html
Hanine, S., Dinar, B.: The challenges of human capital management in the VUCA era. J. Hum. Resour. Sustainab. Stud. 10, 503–514 (2022). https://doi.org/10.4236/jhrss.2022.103030
Biswas, S.S.: Role of chat GPT in public health. Ann. Biomed. Eng. (2023). https://doi.org/10.1007/s10439-023-03172-7
Rudolph, J., Tan, S., Tan, S.: ChatGPT: bullshit spewer or the end of traditional assessments in higher education? J. Appl. Learn. Teach. 6 (2023). https://doi.org/10.37074/jalt.2023.6.1.9
King, M.R.: ChatGPT: a conversation on artificial intelligence, chatbots, and plagiarism in higher education. Cell. Mol. Bioeng. 16, 1–2 (2023). https://doi.org/10.1007/s12195-022-00754-8
Lahat, A., Shachar, E., Avidan, B., Shatz, Z., Glicksberg, B.S., Klang, E.: Evaluating the use of large language model in identifying top research questions in gastroenterology. Sci. Rep. 13, 4164 (2023). https://doi.org/10.1038/s41598-023-31412-2
Pourhoseingholi, M.A., Hatamnejad, M.R., Solhpour, A.: Does ChatGPT (or any other artificial intelligence language tools) deserve to be included in authorship list? Gastroenterol Hepatol Bed Bench (2023). https://doi.org/10.22037/ghfbb.v16i1.2747
Lund, B.D., Wang, T.: Chatting about ChatGPT: how may AI and GPT impact academia and libraries? Library Hi Tech News. preprint (2023). https://doi.org/10.1108/LHTN-01-2023-0009
Dwivedi, Y.K., et al.: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. Int. J. Inf. Manage. 71, 102642 (2023). https://doi.org/10.1016/j.ijinfomgt.2023.102642
Loconte, R., Orrù, G., Tribastone, M., Pietrini, P., Sartori, G.: Challenging ChatGPT’s “intelligence” with human tools: A neuropsychological investigation on prefrontal functioning of a large language model. SSRN. https://doi.org/10.2139/ssrn.4377371
OpenAI: Models. https://platform.openai.com/docs/models/gpt-3 (2023)
Flesch, R.: A new readability yardstick. J. Appl. Psychol. 32, 221–233 (1948). https://doi.org/10.1037/h0057532
Bovair, S., Kieras, D.E., Poison, P.G.: The acquisition and performance of text-editing skill: a cognitive complexity analysis. Hum. Comput. Interact. 5, 1–48 (1990). https://doi.org/10.1207/s15327051hci0501_1
Johnson, M.D.: Cognitive task complexity and L2 written syntactic complexity, accuracy, lexical complexity, and fluency: a research synthesis and meta-analysis. J. Second. Lang. Writ. 37, 13–38 (2017). https://doi.org/10.1016/j.jslw.2017.06.001
Besharati, M., Izadi, M.: DAST Model: Deciding About Semantic Complexity of a Text (2019)
Pallotti, G.: A simple view of linguistic complexity. Second. Lang. Res. 31, 117–134 (2015). https://doi.org/10.1177/0267658314536435
Lourdes, O.: Syntactic complexity measures and their relationship to L2 proficiency: a research synthesis of college level L2 writing. Appl. Linguist. 24, 492–518 (2003). https://doi.org/10.1093/applin/24.4.492
Park, H.M.: Comparing group means: t-tests and one-way ANOVA using Stata, SAS, R, and SPSS (2009). https://hdl.handle.net/2022/19735
Kleinbaum, D.G., Klein, M.: Logistic Regression. Springer, New York, NY (2010). https://doi.org/10.1007/978-1-4419-1742-3
Hair, J.F., Black, W.C., Babin, B.J., Anderson, R.E.: Multivariate data analysis. Pearson, Noida, India (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix a: Sample Responses by ChatGPT
Appendix a: Sample Responses by ChatGPT
Question | ChatGPT response | Correctness |
---|---|---|
I was facing East and turned 180°, which direction am I facing now? | You are now facing West | Yes |
How much is 135°plus 45°? | 180° | Yes |
I was facing East and turned 135° plus 45°, which direction am I facing now? | You are now facing South-Southeast | No |
The afternoon sun is behind me - which direction am I facing? | You are facing west | No |
I was facing East and turned 180° twice, which direction am I facing now? | You are now facing West | No |
Name a fruit that starts with b | Banana | Yes |
Name a fruit that starts with b and ends with y | Blueberry | Yes |
Name a fruit that starts with b and ends with y and contains a in between | Banana | No |
What is the king’s son called? | The king’s son is typically referred to as the crown prince or the prince | Yes |
What is the king’s son’s mother called? | The king’s son’s mother is typically referred to as the queen or the queen mother | Yes |
What is the king’s son’s mother’s son called? | The king’s son’s mother’s son is called the king’s grandson | No |
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dhar, S., Bose, I. (2024). Are We Nearing Singularity? A Study of Language Capabilities of ChatGPT. In: Dhar, S., Goswami, S., Dinesh Kumar, U., Bose, I., Dubey, R., Mazumdar, C. (eds) AGC 2023. AGC 2023. Communications in Computer and Information Science, vol 2008. Springer, Cham. https://doi.org/10.1007/978-3-031-50815-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-50815-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50814-1
Online ISBN: 978-3-031-50815-8
eBook Packages: Computer ScienceComputer Science (R0)