Measurable impacts of LLM-powered document intelligence on M&A due diligence
Abstract and keywords
Abstract (English):
This review quantifies how large language model (LLM) powered document intelligence, including retrieval augmented generation (RAG) and agentic AI, is reshaping buy side M&A due diligence in mid market deals. We conduct a rapid evidence assessment across regulatory and professional surveys, industry case studies, peer reviewed studies, and vendor whitepapers. We focus on measurable indicators: time to review, issue detection quality, and human in the loop controls. Triangulated findings show 70–75% reductions in document review time versus manual baselines. Optimized RAG configurations reach contract analysis accuracy up to 95%, matching or surpassing earlier machine learning tools. Banks, private equity firms, and law firms report faster deal cycles, stronger risk flagging, and maintained or improved quality with appropriate oversight. Humans in the loop remain essential to manage hallucinations and privacy constraints without erasing efficiency gains. The study consolidates metrics from real deployments and highlights governance practices required for adoption in the mid market.

Keywords:
M&A due diligence, large language models, generative AI, document review, retrieval-augmented generation, efficiency, legaltech, mid-market transactions
Text
Text (PDF): Read Download
References

1. D. Acemoglu, L. Bursztyn, M. Demirer, L. Fahey, R. Galbiati, I. Méjean, S. Noy, S. Peng, J. Regier, and W. Zhang, “The simple macroeconomics of AI,” NBER Working Paper No. 32487, 2024, doi:https://doi.org/10.3386/w32487.

2. J. Villasenor, “Generative artificial intelligence and the practice of law: Impact, opportunities, and risks,” Minnesota Journal of Law, Science & Technology, vol. 25, p. 25, 2023.

3. Litera, “Technology in M&A report: AI, tech adoption, and talent management in US and Canada,” 2023. [Online]. Available: https://info.litera.com/north-america-tech-in-mergers-and-acquisitions-survey-report. Accessed: Sep. 25, 2025.

4. Bain & Company, “Generative AI in M&A: You’re not behind—yet,” 2025 M&A Report, Feb. 4, 2025. [Online]. Available: https://www.bain.com/insights/generative-ai-m-and-a-report-2025/. Accessed: Sep. 28, 2025.

5. M. Jang and G. Stikkel, “Leveraging natural language processing and large language models for assisting due diligence in the legal domain,” in Proc. NAACL-HLT 2024, Industry Track, June 2024, pp. 155–164. Association for Computational Linguistics.

6. EY, “How AI will impact due diligence in M&A transactions,” 2024. [Online]. Available: https://www.ey.com/en_ch/insights/strategy-transactions/how-ai-will-impact-due-diligence-in-m-and-a-transactions. Accessed: Sep. 30, 2025.

7. M. Deshpande, “Accelerating M&A: AI-driven data acquisition guide for integration program managers,” Journal of Artificial Intelligence, Machine Learning & Data Science, vol. 1, no. 4, pp. 642–647, 2023.

8. Addleshaw Goddard, “Harnessing the power of large language models for legal document review—The RAG Report: Can LLMs be good enough for legal due diligence?,” Addleshaw Goddard LLP Innovation Research, 2024. [Online]. Available: https://www.addleshawgoddard.com. Accessed: Sep. 20, 2025.

9. Artificial Lawyer, “AG proves LLMs can do well on due diligence,” Oct. 8, 2024. [Online]. Available: https://www.artificiallawyer.com/2024/10/08/ag-proves-llms-can-do-well-on-due-diligence/. Accessed: Sep. 22, 2025.

10. Bain & Company, “Generative AI in M&A: Where hope meets hype,” 2024. (Referenced in: I. Käyhkö, The Disruption of Due Diligence, Aalto University, 2025).

11. Deloitte Legal, “The future of legal work? The use of generative AI by legal departments,” Deloitte (UK) Survey Report, June 2024. [Online]. (Excerpt via Lexology). Accessed: Oct. 8, 2025.

12. Z. Han, “Does AI adoption in M&A teams improve deal performance?,” SSRN Working Paper No. 5128530, Dec. 27, 2024.

13. M. A. Bedekar et al., “AI in mergers and acquisitions: Analyzing the effectiveness of artificial intelligence in due diligence,” in Proc. 2024 Int. Conf. on Knowledge Engineering and Communication Systems (ICKECS 2024), Apr. 2024, pp. 1–5, doi:https://doi.org/10.1109/ICKECS.2024.10616599.

14. Y. Zhao et al., “Utilizing large language models for information extraction from real estate transactions,” arXiv:2404.18043 [cs.CL], Apr. 2024.

15. OpenLedger, “AI in M&A accounting: Transforming financial due diligence in 2025,” 2025. [Online]. Available: https://www.openledger.com/future-of-ai-in-accounting/ai-in-m-a-accounting-transforming-financial-due-diligence-in-2025. Accessed: Sep. 28, 2025.

Login or Create
* Forgot password?