@article{loughran2011,
  author  = {Loughran, Tim and McDonald, Bill},
  title   = {When Is a Liability Not a Liability? {T}extual Analysis, Dictionaries, and 10-{K}s},
  journal = {Journal of Finance},
  year    = {2011}, volume = {66}, number = {1}, pages = {35--65},
  doi     = {10.1111/j.1540-6261.2010.01625.x}
}
@article{loughran2016,
  author  = {Loughran, Tim and McDonald, Bill},
  title   = {Textual Analysis in Accounting and Finance: A Survey},
  journal = {Journal of Accounting Research},
  year    = {2016}, volume = {54}, number = {4}, pages = {1187--1230},
  doi     = {10.1111/1475-679X.12123}
}
@article{hoberg2016,
  author  = {Hoberg, Gerard and Phillips, Gordon},
  title   = {Text-Based Network Industries and Endogenous Product Differentiation},
  journal = {Journal of Political Economy},
  year    = {2016}, volume = {124}, number = {5}, pages = {1423--1465},
  doi     = {10.1086/688176}
}
@article{hobergmaksimovic2015,
  author  = {Hoberg, Gerard and Maksimovic, Vojislav},
  title   = {Redefining Financial Constraints: A Text-Based Analysis},
  journal = {Review of Financial Studies},
  year    = {2015}, volume = {28}, number = {5}, pages = {1312--1352},
  doi     = {10.1093/rfs/hhu089}
}
@article{gentzkow2019,
  author  = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},
  title   = {Text as Data},
  journal = {Journal of Economic Literature},
  year    = {2019}, volume = {57}, number = {3}, pages = {535--574},
  doi     = {10.1257/jel.20181020}
}
@article{hassan2019,
  author  = {Hassan, Tarek A. and Hollander, Stephan and van Lent, Laurence and Tahoun, Ahmed},
  title   = {Firm-Level Political Risk: Measurement and Effects},
  journal = {Quarterly Journal of Economics},
  year    = {2019}, volume = {134}, number = {4}, pages = {2135--2202},
  doi     = {10.1093/qje/qjz021}
}
@article{cohen2020,
  author  = {Cohen, Lauren and Malloy, Christopher and Nguyen, Quoc},
  title   = {Lazy Prices},
  journal = {Journal of Finance},
  year    = {2020}, volume = {75}, number = {3}, pages = {1371--1415},
  doi     = {10.1111/jofi.12885}
}
@article{kelly2021,
  author  = {Kelly, Bryan and Papanikolaou, Dimitris and Seru, Amit and Taddy, Matt},
  title   = {Measuring Technological Innovation over the Long Run},
  journal = {American Economic Review: Insights},
  year    = {2021}, volume = {3}, number = {3}, pages = {303--320},
  doi     = {10.1257/aeri.20190499}
}
@article{dyer2017,
  author  = {Dyer, Travis and Lang, Mark and Stice-Lawrence, Lorien},
  title   = {The Evolution of 10-{K} Textual Disclosure: Evidence from {L}atent {D}irichlet {A}llocation},
  journal = {Journal of Accounting and Economics},
  year    = {2017}, volume = {64}, number = {2--3}, pages = {221--245},
  doi     = {10.1016/j.jacceco.2017.07.002}
}
@article{li2021,
  author  = {Li, Kai and Mai, Feng and Shen, Rui and Yan, Xinyan},
  title   = {Measuring Corporate Culture Using Machine Learning},
  journal = {Review of Financial Studies},
  year    = {2021}, volume = {34}, number = {7}, pages = {3265--3315},
  doi     = {10.1093/rfs/hhaa079}
}
@article{grimmer2013,
  author  = {Grimmer, Justin and Stewart, Brandon M.},
  title   = {Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts},
  journal = {Political Analysis},
  year    = {2013}, volume = {21}, number = {3}, pages = {267--297},
  doi     = {10.1093/pan/mps028}
}
@article{fellegi1969,
  author  = {Fellegi, Ivan P. and Sunter, Alan B.},
  title   = {A Theory for Record Linkage},
  journal = {Journal of the American Statistical Association},
  year    = {1969}, volume = {64}, number = {328}, pages = {1183--1210},
  doi     = {10.1080/01621459.1969.10501049}
}
@book{christen2012,
  author    = {Christen, Peter},
  title     = {Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection},
  publisher = {Springer},
  address   = {Berlin},
  year      = {2012},
  doi       = {10.1007/978-3-642-31164-2}
}
@inproceedings{reimers2019,
  author    = {Reimers, Nils and Gurevych, Iryna},
  title     = {Sentence-{BERT}: Sentence Embeddings using {S}iamese {BERT}-Networks},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP)},
  year      = {2019}, pages = {3982--3992},
  doi       = {10.18653/v1/D19-1410}
}
@inproceedings{raasveldt2019,
  author    = {Raasveldt, Mark and M{\"u}hleisen, Hannes},
  title     = {{DuckDB}: An Embeddable Analytical Database},
  booktitle = {Proceedings of the 2019 International Conference on Management of Data (SIGMOD)},
  year      = {2019}, pages = {1981--1984},
  doi       = {10.1145/3299869.3320212}
}
@misc{secfairaccess,
  author       = {{U.S. Securities and Exchange Commission}},
  title        = {Accessing {EDGAR} Data: Fair Access Policy},
  howpublished = {\url{https://www.sec.gov/search-filings/edgar-search-assistance/accessing-edgar-data}},
  year         = {2026},
  note         = {Accessed October 2026; URL re-verified November 5, 2026 (the former \texttt{/os/accessing-edgar-data} address redirects here)}
}
@misc{ftserussell2026,
  author       = {{FTSE Russell}},
  title        = {Russell {US} Equity Indexes: Construction and Methodology, v7.2},
  howpublished = {\url{https://www.lseg.com/content/dam/ftse-russell/en_us/documents/ground-rules/russell-us-indexes-construction-and-methodology.pdf}},
  year         = {2026},
  month        = {August},
  note         = {Document dated August 2026; downloaded November 5, 2026}
}
@misc{ftserussell3000factsheet2026,
  author       = {{FTSE Russell}},
  title        = {Russell 3000 Index Factsheet},
  howpublished = {\url{https://research.ftserussell.com/Analytics/FactSheets/Home/DownloadSingleIssue?issueName=US3000USD}},
  year         = {2026},
  note         = {Index characteristics as of September 30, 2026 (2,996 holdings); downloaded November 5, 2026}
}
@techreport{spid2026,
  author      = {Tandjambianda, Djerrycharli and Boucher, Simon-Pierre and Kammoun, Manel},
  title       = {{SPID} --- {SEC} Project Intelligence Database: A Methodological Report on the {S\&P}~500 Release},
  institution = {Université du Québec en Outaouais, Département des sciences administratives},
  type        = {Unpublished internal methodological report, available from the authors},
  year        = {2026},
  note        = {June 2026 study of revision \texttt{df7905d}; the report file was regenerated on October 28, 2026}
}
@techreport{kammoun2026ai,
  author      = {Kammoun, Manel and Tandjambianda, Djerrycharli and Boucher, Simon-Pierre},
  title       = {Does the Language of Artificial Intelligence Move Markets? {A} Semantic Analysis of {R}ussell~3000 {SEC} Filings and the Cross-Section of Stock Returns, 2010--2026},
  institution = {Université du Québec en Outaouais, Département des sciences administratives},
  type        = {UQO Working Paper (FIRC)},
  number      = {0002},
  year        = {2026},
  note        = {Version 2.0, October 28, 2026}
}
@misc{iwvholdings2026,
  author       = {{BlackRock, Inc.}},
  title        = {{iShares} {R}ussell 3000 {ETF} ({IWV}): Fund holdings file (\texttt{latest-holdings.csv})},
  howpublished = {\url{https://www.ishares.com/us/products/239714/ishares-russell-3000-etf}},
  year         = {2026},
  note         = {Holdings as of October 23, 2026, downloaded October 27, 2026; subject to the iShares website terms of use; the downloaded file is not archived with the paper}
}
@misc{wikipediasp500,
  author       = {{Wikipedia contributors}},
  title        = {List of {S\&P} 500 companies},
  howpublished = {\url{https://en.wikipedia.org/wiki/List_of_S%26P_500_companies}},
  year         = {2026},
  note         = {Table scraped May 25, 2026; text available under the Creative Commons Attribution-ShareAlike 4.0 licence}
}
@article{kalyani2025,
  author  = {Kalyani, Aakash and Bloom, Nicholas and Carvalho, Marcela and Hassan, Tarek and Lerner, Josh and Tahoun, Ahmed},
  title   = {The Diffusion of New Technologies},
  journal = {Quarterly Journal of Economics},
  year    = {2025}, volume = {140}, number = {2}, pages = {1299--1365},
  doi     = {10.1093/qje/qjaf002},
  note    = {Published version of NBER Working Paper 28999 (2021, DOI 10.3386/w28999)}
}
@techreport{jha2024,
  author      = {Jha, Manish and Qian, Jialin and Weber, Michael and Yang, Baozhong},
  title       = {{ChatGPT} and Corporate Policies},
  institution = {National Bureau of Economic Research}, type = {NBER Working Paper}, number = {32161},
  year        = {2024}, doi = {10.3386/w32161}
}
@article{ludwig2025,
  author  = {Ludwig, Jens and Mullainathan, Sendhil and Rambachan, Ashesh},
  title   = {Large Language Models: An Applied Econometric Framework},
  journal = {Annual Review of Economics},
  year    = {2026}, volume = {18}, number = {1}, pages = {283--316},
  doi     = {10.1146/annurev-economics-120925-105620},
  note    = {Also NBER Working Paper 33344 (2025, DOI 10.3386/w33344)}
}
@article{gilardi2023,
  author  = {Gilardi, Fabrizio and Alizadeh, Meysam and Kubli, Maël},
  title   = {{ChatGPT} outperforms crowd workers for text-annotation tasks},
  journal = {Proceedings of the National Academy of Sciences},
  year    = {2023}, volume = {120}, number = {30}, pages = {e2305016120},
  doi     = {10.1073/pnas.2305016120}
}
@article{dekok2025,
  author  = {de Kok, Ties},
  title   = {{ChatGPT} for Textual Analysis? How to Use Generative {LLMs} in Accounting Research},
  journal = {Management Science},
  year    = {2025}, volume = {71}, number = {9}, pages = {7888--7906},
  doi     = {10.1287/mnsc.2023.03253}
}
@techreport{kim2023,
  author      = {Kim, Alex G. and Muhn, Maximilian and Nikolaev, Valeri V.},
  title       = {From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI},
  institution = {SSRN}, type = {Working paper}, number = {4593660},
  year        = {2023}, doi = {10.2139/ssrn.4593660}
}
@misc{dolphin2026,
  author       = {Dolphin, Rian and Dursun, Joe and Blankenship, Jarrett and Adams, Katie and Pike, Quinton},
  title        = {Grounded Event Extraction from {SEC} {8-K} Filings with a Fine-Grained Taxonomy},
  howpublished = {arXiv:2607.08346; also SSRN 7087858 (DOI 10.2139/ssrn.7087858)},
  year         = {2026}, doi = {10.48550/arXiv.2607.08346}
}
@techreport{crane2024,
  author      = {Crane, Leland D. and Green, Emily and Harnish, Molly and McClennan, Will and Soto, Paul E. and Vrankovich, Betsy and Williams, Jacob},
  title       = {Tracking Real Time Layoffs with {SEC} Filings: A Preliminary Investigation},
  institution = {Board of Governors of the Federal Reserve System}, type = {Finance and Economics Discussion Series}, number = {2024-020},
  year        = {2024}, doi = {10.17016/feds.2024.020}
}
@inproceedings{loukas2021,
  author    = {Loukas, Lefteris and Fergadiotis, Manos and Androutsopoulos, Ion and Malakasiotis, Prodromos},
  title     = {{EDGAR-CORPUS}: Billions of Tokens Make The World Go Round},
  booktitle = {Proceedings of the Third Workshop on Economics and Natural Language Processing},
  year      = {2021}, pages = {13--18},
  doi       = {10.18653/v1/2021.econlp-1.2}
}
@misc{bettencourt2026,
  author       = {Bettencourt, Nick and Ding, Xiaowei and Giesecke, Kay},
  title        = {The {Stanford} {EDGAR} Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data},
  howpublished = {arXiv:2606.18192; also SSRN 7161699 (DOI 10.2139/ssrn.7161699)},
  year         = {2026}, doi = {10.48550/arXiv.2606.18192}
}
@article{greenstone2010,
  author  = {Greenstone, Michael and Hornbeck, Richard and Moretti, Enrico},
  title   = {Identifying Agglomeration Spillovers: Evidence from Winners and Losers of Large Plant Openings},
  journal = {Journal of Political Economy},
  year    = {2010}, volume = {118}, number = {3}, pages = {536--598},
  doi     = {10.1086/653714}
}
@article{mcconnell1985,
  author  = {McConnell, J and Muscarella, Chris J.},
  title   = {Corporate capital expenditure decisions and the market value of the firm},
  journal = {Journal of Financial Economics},
  year    = {1985}, volume = {14}, number = {3}, pages = {399--422},
  doi     = {10.1016/0304-405X(85)90006-6}
}
@misc{yang2024,
  author       = {Yang, Daniel and Tsai, Yao-Hung Hubert and Yamada, Makoto},
  title        = {On Verbalized Confidence Scores for {LLMs}},
  howpublished = {arXiv:2412.14737},
  year         = {2024}, doi = {10.48550/arXiv.2412.14737}
}
@inproceedings{ye2024,
  author    = {Ye, Fanghua and Yang, Mingming and Pang, Jianhui and Wang, Longyue and Wong, Derek and Yilmaz, Emine and Shi, Shuming and Tu, Zhaopeng},
  title     = {Benchmarking {LLMs} via Uncertainty Quantification},
  booktitle = {Advances in Neural Information Processing Systems 37 (NeurIPS 2024)},
  year      = {2024}, pages = {15356--15385},
  doi       = {10.52202/079017-0491}
}
@article{li2020,
  author  = {Li, Yuliang and Li, Jinfeng and Suhara, Yoshihiko and Doan, AnHai and Tan, Wang-Chiew},
  title   = {Deep entity matching with pre-trained language models},
  journal = {Proceedings of the VLDB Endowment},
  year    = {2020}, volume = {14}, number = {1}, pages = {50--60},
  doi     = {10.14778/3421424.3421431}
}
@misc{peeters2023,
  author       = {Peeters, Ralph and Steiner, Aaron and Bizer, Christian},
  title        = {Entity Matching using Large Language Models},
  howpublished = {arXiv:2310.11244},
  year         = {2023}, doi = {10.48550/arXiv.2310.11244}
}
@article{bellstam2021,
  author  = {Bellstam, Gustaf and Bhagat, Sanjai and Cookson, J. Anthony},
  title   = {A Text-Based Analysis of Corporate Innovation},
  journal = {Management Science},
  year    = {2021}, volume = {67}, number = {7}, pages = {4004--4031},
  doi     = {10.1287/mnsc.2020.3682}
}
@article{sautner2023,
  author  = {Sautner, Zacharias and van Lent, Laurence and Vilkov, Grigory and Zhang, Ruishen},
  title   = {Firm-Level Climate Change Exposure},
  journal = {Journal of Finance},
  year    = {2023}, volume = {78}, number = {3}, pages = {1449--1498},
  doi     = {10.1111/jofi.13219}
}
@article{afzal2026,
  author  = {Afzal, Muhammad Talha and Yan, Jinqiu (Claire) and Li, Huaxia and Vasarhelyi, Miklos},
  title   = {Beyond the bottom line: using generative AI to extract narrative financial disclosures},
  journal = {International Journal of Accounting Information Systems},
  year    = {2026}, volume = {57}, pages = {100777},
  doi     = {10.1016/j.accinf.2026.100777}
}
@techreport{zolas2020,
  author      = {Zolas, Nikolas and Kroff, Zachary and Brynjolfsson, Erik and McElheran, Kristina and Beede, David and Buffington, Cathy and Goldschlag, Nathan and Foster, Lucia and Dinlersoz, Emin},
  title       = {Advanced Technologies Adoption and Use by U.S. Firms: Evidence from the Annual Business Survey},
  institution = {National Bureau of Economic Research}, type = {NBER Working Paper}, number = {28290},
  year        = {2020}, doi = {10.3386/w28290}
}