ChatGPT for Textual Analysis? How to Use Generative LLMs in Accounting Research
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Generative large language models (GLLMs), such as ChatGPT and GPT-4 by OpenAI, are emerging as powerful tools for textual analysis tasks in accounting research. GLLMs can solve any textual analysis task solvable using nongenerative methods as well as tasks previously only solvable using human coding. Whereas GLLMs are new and powerful, they also come with limitations and present new challenges that require care and due diligence. This paper highlights the applications of GLLMs for accounting research and compares them with existing methods. It also provides a framework on how to effectively use GLLMs by addressing key considerations, such as model selection, prompt engineering, and ensuring construct validity. In a case study, I demonstrate the capabilities of GLLMs by detecting nonanswers in earnings conference calls, a traditionally challenging task to automate. The new GPT method achieves an accuracy of 96% and reduces the nonanswer error rate by 70% relative to the existing Gow et al. (2021) method. Finally, I discuss the importance of addressing bias, replicability, and data sharing concerns when using GLLMs. Taken together, this paper provides researchers, reviewers, and editors with the knowledge and tools to effectively use and evaluate GLLMs for academic research. This paper was accepted by Eric So, accounting. Funding: Supported by the Foster School of Business – University of Washington. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.03253 .
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10‐Ks
LOUGHRAN, T., & MCDONALD, B. (2011) · The Journal of Finance · doi:10.1111/j.1540-6261.2010.01625.x · Cited by 6,015
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Lost in the Middle: How Language Models Use Long Contexts
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2023) · arXiv · doi:10.48550/arxiv.2307.03172 · Cited by 1,599
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Sun, Y., Wang, S., Feng, S., Ding, S., Pang, C., Shang, J., Liu, J., Chen, X., Zhao, Y., Lu, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.02137 · Cited by 186
Corporate Scandals and Regulation
HAIL, L., TAHOUN, A., & WANG, C. (2018) · Journal of Accounting Research · doi:10.1111/1475-679x.12201 · Cited by 111
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
Black, S., Biderman, S., Hallahan, E., Anthony, Q., Gao, L., Golding, L., He, H., Leahy, C., McDonell, K., Phang, J., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.06745 · Cited by 67
Cited by
Caution Ahead: Numerical Reasoning and Look‐Ahead Bias in AI Models
LEVY, B. (2026) · Journal of Accounting Research · doi:10.1111/1475-679x.70058 · Cited by 20
Metadata
- Authors
- de Kok, T.
- Venue
- Management Science
- Published
- 2025-09
- Volume
- 71
- Issue
- 9
- Pages
- 7888-7906
- ISSN
- 0025-1909 (ISSN-L)
- 1526-5501
- OpenAlex
- W4406303276
- Cited by
- 160
- References
- 11
- FWCI
- 219.61
- Type
- journal article
- Language
- en
- Open access
- green
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 for Textual Analysis? How to Use Generative LLMs in Accounting Research. https://app.cochat.ai/papers/10.1287/mnsc.2023.03253
- The paper
- de Kok, T. (2025). ChatGPT for Textual Analysis? How to Use Generative LLMs in Accounting Research. Management Science. https://doi.org/10.1287/mnsc.2023.03253
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.