ChatGPT Usage and Limitations
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Large language models have been shown useful in multiple domains including conversational agents, education, and explainable AI.ChatGPT is a large language model developed by OpenAI as a conversational agent. Being a large language model, ChatGPT is trained on massive amounts of data. Clearly, the characteristics of the data influence ChatGPT's responses. In this paper, we stress a surprising bias of ChatGPT related to the use of digits in numbers. Namely, we show a very high correlation between the frequency of digits generated by ChatGPT and humans' favorite numbers, with the most frequent digit generated by ChatGPT, matching humans' most favorable number, $7$. We also show some advantages of ChatGPT being developed as a conversational agent, and discuss some of its limitations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
GPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519
Economic games on the internet: the effect of $1 stakes
Amir, O., Rand, D. G., & Gal, Y. K. (2012) · PLoS ONE · doi:10.1371/journal.pone.0031461 · Cited by 364
Conversational Agents: Goals, Technologies, Vision and Challenges
Allouch, M., Azaria, A., & Azoulay, R. (2021) · Sensors · doi:10.3390/s21248448 · Cited by 168
Self-citationInstructable Intelligent Personal Agent
Azaria, A., Krishnamurthy, J., & Mitchell, T. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10357 · Cited by 70
Self-citation
Cited by
Dwivedi, Y. K., Kshetri, N., Hughes, L., Slade, E. L., Jeyaraj, A., Kar, A. K., Baabdullah, A. M., Koohang, A., Raghavan, V., Ahuja, M., et al. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102642 · Cited by 4,584
A SWOT analysis of ChatGPT: Implications for educational practice and research
Farrokhnia, M., Banihashem, S. K., Noroozi, O., & Wals, A. (2024) · Innovations in Education and Teaching International · doi:10.1080/14703297.2023.2195846 · Cited by 1,384
Grassini, S. (2023) · Education Sciences · doi:10.3390/educsci13070692 · Cited by 1,048
ChatGPT: Jack of all trades, master of none
Kocoń, J., Cichecki, I., Kaszyca, O., Kochanek, M., Szydło, D., Baran, J., Bielaniewicz, J., Gruza, M., Janz, A., Kanclerz, K., et al. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101861 · Cited by 758
A Categorical Archive of ChatGPT Failures
Borji, A. (2023) · arXiv · doi:10.48550/arxiv.2302.03494 · Cited by 514
Metadata
- Authors
- Azaria, A.
- Publisher
- Center for Open Science
- Published
- 2022-12-27
- OpenAlex
- W4312213844
- Cited by
- 111
- References
- 5
- Type
- posted content
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: ChatGPT Usage and Limitations. https://app.cochat.ai/papers/10.31219/osf.io/5ue7n
- The paper
- Azaria, A. (2022). ChatGPT Usage and Limitations. https://doi.org/10.31219/osf.io/5ue7n
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.