q-fin.GNOct 22, 2026

Uncertainty Quantification for Financial Foundation Models: A Survey

Authors: Zijie Zhao, Mingjun Sun, Shenbo Xu

Organizations: Massachusetts Institute of Technology Cambridge, MA, USA · Carnegie Mellon University Pittsburgh, PA, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Financial foundation models increasingly support workflows spanning financial question answering, disclosure analysis, forecasting, and decision-making. In these settings, uncertainty may concern whether evidence is valid and available at the relevant time, whether an interpretation is justified, which outcomes remain plausible, or which action is preferred under costs and risk constraints. Because these objects arise at different points in a workflow, uncertainty cannot be reduced to confidence in a final output. We introduce a source-aware framework that distinguishes six sources of uncertainty across evidence and context, model and inference, and outcome and action, while treating agentic workflows as the execution layer through which uncertainty can propagate, change form, or be reduced. We develop a mechanism-based taxonomy grounded in how methods construct or verify uncertainty and reliability representations, and use it to assess their applicability across financial task domains. We further map finance-specific empirical studies across the taxonomy and task domains to characterize the current research landscape. Our analysis shows that most reviewed studies address uncertainty in individual parts of financial workflows, with limited work connecting evidence and reasoning reliability to downstream prediction and constrained action. By connecting where uncertainty arises, how it is represented, and how it bears on downstream decisions, this survey provides a unified foundation for studying and evaluating uncertainty in financial foundation models.

Figures & tables

Figure 1. A source-aware framework for financial uncertainty. The agentic workflow layer connects the six sources as uncertainty propagates, changes form, or is reduced during execution. Six sources of financial uncertainty are organized into evidence and context, model and inference, and outcome and action. An agentic workflow layer spans retrieval, reasoning and planning, tool use, observation and verification, and action, with feedback across iterations.
Task domainRepresentative tasksDominant sources aMost relevant method families
Information and Document IntelligenceRetrieval and RAG; financial QA; information extraction; table, chart, and multimodal document understanding; grounded summarizationUE,UK,URU_{E},U_{K},U_{R}Evidence and Provenance Verification
Analysis, Valuation, and AdvisoryDisclosure and event interpretation; financial-statement analysis; valuation; investment research and due diligence; investment and wealth advisoryUR,UK,UDU_{R},U_{K},U_{D}Direct Uncertainty Estimation; Sampling-Based Consistency Estimation
Forecasting and Risk ModelingReturn, earnings, cash-flow, and volatility forecasting; credit and default risk; VaR/ES; stress testingUO,USU_{O},U_{S}Distributional and Statistical Uncertainty Estimation; Ensemble-Based Uncertainty Estimation
Financial Decision-MakingSecurity selection and trading; portfolio allocation and rebalancing; hedging and position sizing; execution and market making; lending and underwritingUD,UO,USU_{D},U_{O},U_{S}Distributional and Statistical Uncertainty Estimation; Direct Uncertainty Estimation; Ensemble-Based Uncertainty Estimation
Accounting, Compliance, and Financial OperationsAccounting and reporting; regulatory interpretation and compliance review; KYC/AML investigation; audit and internal controls; payments, settlement, reconciliation, and claims reviewUE,UR,UDU_{E},U_{R},U_{D}Evidence and Provenance Verification; Direct Uncertainty Estimation
Table 1. Financial task domains, representative tasks, dominant uncertainty sources, and relevant method families.
Figure 2. Method–task coverage in the included finance-specific studies. Cells report unique-paper counts across 24 papers and 26 assignments; gray denotes zero, orange one, and red more than one study. A five-by-five heatmap of unique-paper counts across five uncertainty method families and five financial task domains. Evidence and provenance verification is concentrated in information and document tasks, while distributional and statistical uncertainty estimation is concentrated in forecasting and risk.
More in this topic

Uncertainty Quantification

Uncertainty quantification estimates how reliable predictions and scientific inferences are, and how uncertainty propagates into decisions.

See all 652 papers

Explore similar work

CardsList
Oct 19, 2026

Toward Structured Financial Foundation Models

Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation models can advance both goals. However, prevailing architectures and objectives do not by themselves address the combined demands of financial systems: partial observability, interacting entities, asynchronous events, changing regimes, action-dependent outcomes, and rare states with disproportionate consequences. Moreover, independently developed specialists may learn incompatible representations, while multi-domain monolithic alternatives couple data access, model updates, and governance. We therefore propose a structured-data-first research agenda centered on modular, domain-specialized financial foundation models connected by a representation fabric for reuse and composition across domains and tasks. These models should maintain persistent financial state across aggregation levels and time horizons, capture its dynamics, and simulate action-conditioned futures, while remaining calibrated across regimes and for tail outcomes. They must also learn efficiently under data and access constraints and provide faithful, traceable explanations. We identify research challenges, directions, and capability-oriented evaluation criteria.

Natraj Raman, Saumitra Mishra, Vamsi Potluru +1

JPMorgan AI Research

FinanceFinancial Services
AskPDF
May 27, 2026

High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models

Recent Tabular Foundation Models (TFMs) have demonstrated state-of-the-art predictive performance, often surpassing Gradient-Boosted Decision Trees (GBDTs). However, the trustworthiness of these models, particularly their uncertainty quantification, has been largely overlooked. We investigate this gap through an extensive study comparing TFMs, GBDTs, and classical baselines on the 112 datasets of the TALENT benchmark. Our results reveal a performance-uncertainty trade-off: although TFMs achieve the highest predictive performance, measured by AUC, they exhibit lower conditional coverage under conformal prediction, measured by SSCS, compared to GBDTs. Complementary experiments on synthetic datasets further characterize the regimes in which this effect intensifies. We conclude that while TFMs advance predictive frontiers, achieving well-calibrated uncertainty remains a major open challenge for their reliable adoption. Code is available at: https://github.com/jose-melo/high-performance-low-reliability

José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel +1

CentraleSup´elec, Universit´e Paris-Saclay Gif-sur-Yvette - France

Tabular Foundation ModelsUncertainty QuantificationConformal PredictionUncertainty Calibration
AskPDF
Jun 2, 2026

BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents

Financial-research answers are decision-relevant only when another analyst can audit how they were produced: which source was chosen, which period and accounting definition were used, which assumptions were made, and how the calculation was performed. Existing finance benchmarks largely evaluate isolated subskills or final answers, leaving the auditable derivation itself under-measured. We introduce BigFinanceBench, a 928-item expert-authored benchmark of open-ended financial-research tasks in which each item pairs a ground-truth reference answer with a point-weighted rubric that decomposes the derivation into independently checkable steps. BigFinanceBench is workflow-grounded in that it evaluates the full derivation rather than only the final output. Across 36,241 rubric points, the benchmark supports partial-credit evaluation and localization of failures across the analyst workflow. Evaluating ten current frontier and open-weight agents, we find substantial headroom: the best system reaches only 58.8% rubric score, final-answer accuracy is a useful but lossy proxy for derivation quality, and model capability varies non-uniformly across financial workflows.

Alex Wang, Georg Meinhardt, Jacob Katz +4

1Rogo · 2OpenAI · †Work done while at Rogo.

Benchmark DesignFinancial QARubric-Based EvaluationFinanceAgent BenchmarksFinancial Reasoning Benchmarks
AskPDF