ChatGPT for Textual Analysis? How to Use Generative LLMs in Accounting Research

References

• Anand V, Bochkay K, Chychyla R, Leone A (2020) Using Python for text analysis in accounting research. Foundations Trends Accounting 14(3–4):128–359.Google Scholar
• Bahdanau D, Cho K, Bengio Y (2016) Neural machine translation by jointly learning to align and translate. Preprint, submitted September 1, https://arxiv.org/abs/1409.0473.Google Scholar
• Bai JJ, Boyson NM, Cao Y, Liu M, Wan C (2023) Executives vs. chatbots: Unmasking insights through human-AI differences in earnings conference Q&A. Preprint, submitted June 22, https://dx.doi.org/10.2139/ssrn.4480056.Google Scholar
• Bernard D, Blankespoor E, de Kok T, Toynbee S (2023) Using GPT models to measure the complexity of business transactions. Preprint, submitted June 25, https://dx.doi.org/10.2139/ssrn.4480309.Google Scholar
• Bhattacharyya M, Miller VM, Bhattacharyya D, Miller LE (2023) High rates of fabricated and inaccurate references in ChatGPT-generated medical content. Cureus 15(5):e39238.Google Scholar
• Black S, Biderman S, Hallahan E, Anthony Q, Gao L, Golding L, He H, et al. (2022) GPT-NeoX-20B: An open-source autoregressive language model. Preprint, submitted April 14, https://arxiv.org/abs/2204.06745.Google Scholar
• Bochkay K, Brown SV, Leone AJ, Tucker JW (2023) Textual analysis in accounting: What’s next? Contemporary Accounting Res. 40(2):765–805.Crossref, Google Scholar
• Brown SV, Tian XS, Tucker JW (2018) The spillover effect of SEC comment letters on qualitative corporate disclosure: Evidence from the risk factor disclosure. Contemporary Accounting Res. 35(2):622–656.Crossref, Google Scholar
• Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, et al. (2020) Language models are few-shot learners. Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H, eds. Advances in Neural Information Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 1877–1901.Google Scholar
• Call AC, Flam RW, Lee JA, Sharp NY (2024) Managers’ use of humor on public earnings conference calls. Rev. Accounting Stud. 29:2650–2687.Crossref, Google Scholar
• Chen L, Zaharia M, Zou J (2023) How is ChatGPT’s behavior changing over time? Preprint, submitted July 18, https://arxiv.org/abs/2307.09009.Google Scholar
• Chuk E, Matsumoto D, Miller GS (2013) Assessing methods of identifying management forecasts: CIG vs. researcher collected. J. Accounting Econom. 55(1):23–42.Crossref, Google Scholar
• Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. Preprint, submitted October 11, https://arxiv.org/abs/1810.04805.Google Scholar
• Gow ID, Larcker DF, Zakolyukina AA (2021) Non-answers during conference calls. J. Accounting Res. 59(4):1349–1384.Crossref, Google Scholar
• Hail L, Tahoun A, Wang C (2018) Corporate scandals and regulation. J. Accounting Res. 56(2):617–671.Crossref, Google Scholar
• Hansen AL, Kazinnik S (2023) Can ChatGPT decipher Fedspeak? Preprint, submitted April 7, https://dx.doi.org/10.2139/ssrn.4399406.Google Scholar
• Hassan TA, Hollander S, van Lent L, Tahoun A (2019) Firm-level political risk: Measurement and Effects. Quart. J. Econom. 134(4):2135–2202.Crossref, Google Scholar
• Hollander S, Pronk M, Roelofsen E (2010) Does silence speak? An empirical analysis of disclosure choices during conference calls. J. Accounting Res. 48(3):531–563.Crossref, Google Scholar
• Hu N, Liang P, Yang X (2023) Whetting all your appetites for financial tasks with one meal from GPT? A comparison of GPT, FinBERT, and dictionaries in evaluating sentiment analysis. Preprint, submitted April 26, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4426455.Google Scholar
• Huang AH, Wang H, Yang Y (2023) FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Res. 40(2):806–841.Crossref, Google Scholar
• Jha M, Qian J, Weber M, Yang B (2024) ChatGPT and corporate policies. Preprint, submitted July 26, https://dx.doi.org/10.2139/ssrn.4521096.Google Scholar
• Kaplan DM, Palitsky R, Arconada Alvarez SJ, Pozzo NS, Greenleaf MN, Atkinson CA, Lam WA (2024) What’s in a name? Experimental evidence of gender bias in recommendation letters generated by ChatGPT. J. Medical Internet Res. 26:e51837.Crossref, Google Scholar
• Kim AG, Muhn M, Nikolaev VV (2024) Bloated disclosures: Can ChatGPT help investors process information? Preprint, submitted April 21, https://dx.doi.org/10.2139/ssrn.4425527.Google Scholar
• Lopez-Lira A, Tang Y (2023) Can ChatGPT forecast stock price movements? Return predictability and large language models. Preprint, submitted April 10, http://dx.doi.org/10.2139/ssrn.4412788.Google Scholar
• OpenAI (2023) GPT-4 technical report. Preprint, submitted March 15, https://arxiv.org/abs/2303.08774.Google Scholar
• Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training. OpenAI (June 11), https://openai.com/index/language-unsupervised/.Google Scholar
• Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI (February 14), https://openai.com/index/better-language-models/.Google Scholar
• Rouen E, Sachdeva K, Yoon A (2023) Sustainability meets substance: Evaluating ESG reports in the context of 10-Ks and firm performance. Preprint, submitted March 15, http://dx.doi.org/10.2139/ssrn.4227934.Google Scholar
• Siano F, Wysocki P (2021) Transfer learning and textual analysis of accounting disclosures: Applying big data methods to small(er) datasets. Accounting Horizons 35(3):217–244.Crossref, Google Scholar
• Sun Y, Wang S, Feng S, Ding S, Pang C, Shang J, Liu J, et al. (2021) ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. Preprint, submitted July 5, https://arxiv.org/abs/2107.02137.Google Scholar
• Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozière B, et al. (2023a) LLaMA: Open and efficient foundation language models. Preprint, submitted February 27, https://arxiv.org/abs/2302.13971.Google Scholar
• Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, et al. (2023b) Llama 2: Open foundation and fine-tuned chat models. Preprint, submitted July 18, https://arxiv.org/abs/2307.09288.Google Scholar
• Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds. Advances in Neural Information Processing Systems, vol. 30 (Curran Associates Inc., Red Hook, NY).Google Scholar
• Wang B, Komatsuzaki A (2021) GPT-J-6B: A 6 billion parameter autoregressive language model. https://github.com/kingoflolz/mesh-transformer-jax.Google Scholar