LAMDA: Large Language Model as Decision Analyst

References

• Abbas AE, Hupman AC, Monger R (2026) Assessing the quality of large language models and human inputs to a decision: A proposed framework and two benchmark case studies. Decision Anal., ePub ahead of print March 25, https://doi.org/10.1287/deca.2025.0467.Link, Google Scholar
• Bodily SE, Furman B (2016) Long-term care insurance decisions. Decision Anal. 13(3):173–191.Link, Google Scholar
• Bordley RF (2023) Lessons for decision-analysis practice from the automotive industry. INFORMS J. Appl. Anal. 53(3):240–246.Link, 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. Adv. Neural Inform. Processing Systems, vol. 33 (Curran Associates Inc., Red Hook, NY), 1877–1901.Google Scholar
• Budescu DV, Por HH, Broomell SB, Smithson M (2014) The interpretation of IPCC probabilistic statements around the world. Nature Climate Change 4(6):508–512.Crossref, Google Scholar
• Dhami MK, Mandel DR (2022) Communicating uncertainty using words and numbers. Trends Cognitive Sci. 26(6):514–526.Crossref, Google Scholar
• Dillon RL, Bier VM, John RS, Althenayyan A (2023) Closing the gap between decision analysis and policy analysts before the next pandemic. Decision Anal. 20(2):109–132.Link, Google Scholar
• Everitt T, Carey R, Langlois ED, Ortega PA, Legg S (2021) Agent incentives: A causal perspective. Proc. AAAI Conf. Artificial Intelligence, vol. 35 (AAAI, Washington, DC), 11487–11495.Google Scholar
• Falconer JR, Frank E, Polaschek DL, Joshi C (2022) Methods for eliciting informative prior distributions: A critical review. Decision Anal. 19(3):189–204.Link, Google Scholar
• Feng Y, Zhou B, Lin W, Roth D (2025) BIRD: A trustworthy Bayesian inference framework for large language models. Internat. Conf. Learn. Representations, vol. 2025 (ICLR, Appleton, WI), 8961–8989.Google Scholar
• Fox J, Everitt T, Carey R, Langlois ED, Abate A, Wooldridge MJ (2021) PyCID: A Python library for causal influence diagrams. SciPy, 65–73.Crossref, Google Scholar
• Gibson DR (2011) Speaking of the future: Contentious narration during the Cuban missile crisis. Qualitative Sociol. 34:503–522.Crossref, Google Scholar
• Gregory R, Fischhoff B, McDaniels T (2005) Acceptable input: Using decision analysis to guide public policy deliberations. Decision Anal. 2(1):4–16.Link, Google Scholar
• Gu J, Jiang X, Shi Z, Tan H, Zhai X, Xu C, Li W, et al.. (2026) A survey on LLM-as-a-judge. The Innovation 7(6):101253.Crossref, Google Scholar
• Guo D, Yang D, Zhang H, Song J, Wang P, Zhu Q, Xu R, et al. (2025) DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081):633–638.Crossref, Google Scholar
• Howard RA, Matheson JE (2005a) Influence diagram retrospective. Decision Anal. 2(3):144–147.Link, Google Scholar
• Howard RA, Matheson JE (2005b) Influence diagrams. Decision Anal. 2(3):127–143.Link, Google Scholar
• Huang J, Yang DM, Rong R, Nezafati K, Treager C, Chi Z, Wang S, et al. (2024) A critical assessment of using ChatGPT for extracting structured data from clinical notes. NPJ Digital Medicine 7(1):106.Crossref, Google Scholar
• Karvetski CW, Meinel C, Maxwell DT, Lu Y, Mellers BA, Tetlock PE (2022) What do forecasting rationales reveal about thinking patterns of top geopolitical forecasters? Internat. J. Forecasting 38(2):688–704.Crossref, Google Scholar
• Keating LM, Randall L, Stanton R, McCormack C, Lucid M, Seaborn T, Converse SJ, Canessa S, Moehrenschlager A (2023) Using decision analysis to determine the feasibility of a conservation translocation. Decision Anal. 20(4):295–310.Link, Google Scholar
• Keeney RL (1996) Value-Focused Thinking: A Path to Creative Decisionmaking (Harvard University Press, Cambridge, MA).Crossref, Google Scholar
• Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. Adv. Neural Inform. Processing Systems 35:22199–22213.Google Scholar
• Liu O, Fu D, Yogatama D, Neiswanger W (2025) DeLLMa: Decision making under uncertainty with large language models. Internat. Conf. Learn. Representations, vol. 2025 (ICLR, Appleton, WI), 43850–43886.Google Scholar
• Madaan A, Tandon N, Gupta P, Hallinan S, Gao L, Wiegreffe S, Alon U, et al. (2023) SELF-REFINE: Iterative refinement with self-feedback. Adv. Neural Inform. Processing Systems, vol. 36 (Curran Associates Inc., Red Hook, NY), 46534–46594.Google Scholar
• Matheson D, Matheson JE (2005) Describing and valuing interventions that observe or control decision situations. Decision Anal. 2(3):165–181.Link, Google Scholar
• Merrick JR, McLay LA (2010) Is screening cargo containers for smuggled nuclear threats worthwhile? Decision Anal. 7(2):155–171.Link, Google Scholar
• National Health Commission of the People’s Republic of China (2024) Diagnosis and treatment protocol for human avian influenza (2024 edition). Technical Report Document 268 (2024), National Health Commission of the People’s Republic of China, Beijing. https://www.nhc.gov.cn/ylyjs/gzdt/202407/430f72d43b4c4d70b 12f0edbbf9eaf94/files/1734003043606_85634.pdf.Google Scholar
• Perlis RH, Goldberg JF, Ostacher MJ, Schneck CD (2024) Clinical decision support for bipolar depression using large language models. Neuropsychopharmacology 49(9):1412–1416.Crossref, Google Scholar
• Regnier ED, Feldmeier JW (2022) D minus months: Strategic planning for weather-sensitive decisions. Decision Anal. 19(1):1–20.Link, Google Scholar
• Sandmann S, Hegselmann S, Fujarski M, Bickmann L, Wild B, Eils R, Varghese J (2025) Benchmark evaluation of DeepSeek large language models in clinical decision-making. Nature Med. 31(8):2546–2549.Crossref, Google Scholar
• Schoenegger P, Jones CR, Tetlock PE, Mellers B (2025) Prompt engineering large language models’ forecasting capabilities. Preprint, submitted June 2, https://arxiv.org/abs/2506.01578.Google Scholar
• Shachter RD, Bhattacharjya D (2011) Solving Influence Diagrams: Exact Algorithms (Wiley, New York).Google Scholar
• Simon J, Siebert JU (2025) ChatGPT vs. experts: Can GenAI develop high-quality organizational and policy objectives? Decision Anal., ePub ahead of print November 11, https://doi.org/10.1287/deca.2025.0387.Link, Google Scholar
• Stonebraker JS (2023) Case article—Bayer new drug development decision making. INFORMS Trans. Ed. 23(3):154–158.Link, Google Scholar
• von Winterfeldt D (2013) Bridging the gap between science and decision making. Proc. Natl. Acad. Sci. USA 110(Suppl 3):14055–14061.Crossref, Google Scholar
• Wan Q, Xu X, Hunt K, Zhuang J (2022) Stay home or not? Modeling individuals’ decisions during the COVID-19 pandemic. Decision Anal. 19(4):319–336.Link, Google Scholar
• Wang X, Wei J, Schuurmans D, Le QV, Chi EH, Narang S, Chowdhery A, Zhou D (2023) Self-consistency improves chain of thought reasoning in language models. Eleventh Internat. Conf. Learn. Representations (Kigali, Rwanda).Google Scholar
• Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi E, Le QV, Zhou D, et al. (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inform. Processing Systems 35:24824–24837.Google Scholar
• Xia S, Lu B, Eisner J (2024) Let’s think var-by-var: Large language models enable ad hoc probabilistic reasoning. Preprint, submitted December 3, https://arxiv.org/abs/2412.02081.Google Scholar
• Xiao Z, Zhang D, Wu Y, Xu L, Wang Y, Han X, Fu X, et al. (2024) Chain-of-experts: When LLMs meet complex operations research problems. Internat. Conf. Learn. Representations, vol. 2024 (ICLR, Appleton, WI), 48519–48537.Google Scholar
• Xiong M, Hu Z, Lu X, Li Y, Fu J, He J, Hooi B (2024) Can LLMs express their uncertainty? An empirical evaluation of confidence elicitation in LLMs. Internat. Conf. Learn. Representations, vol. 2024 (ICLR, Appleton, WI), 23650–23678.Google Scholar
• Yao S, Zhao J, Yu D, Du N, Shafran I, Narasimhan KR, Cao Y (2023) ReAct: Synergizing reasoning and acting in language models. Eleventh Internat. Conf. Learn. Representations (Kigali, Rwanda).Google Scholar
• Ye Y, Cong X, Tian S, Cao J, Wang H, Qin Y, Lu Y, et al. (2023) ProAgent: From robotic process automation to agentic process automation. Preprint, submitted November 23, https://arxiv.org/abs/2311.10751.Google Scholar
• Zhao Z, Lee WS, Hsu D (2023) Large language models as commonsense knowledge for large-scale task planning. Adv. Neural Inform. Processing Systems 36:31967–31987.Google Scholar
• Zhu JQ, Griffiths T (2025) Eliciting the priors of large language models using iterated in-context learning. Proc. Annual Meeting Cognitive Sci. Soc. (San Francisco), vol. 47.Google Scholar