A Methodology for Assessing the Risk of Metric Failure in LLMs Within the Financial Domain

📅 2025-10-15
📈 Citations: 0
Influential: 0
📄 PDF

career value

156K/year
🤖 AI Summary
Traditional machine learning metrics and generic benchmarks frequently fail in financial applications of generative AI, while reliance on subject-matter expert (SME) evaluation introduces subjective bias and systemic risks, leading to erroneous performance assessment. Method: This paper proposes the first LLM evaluation framework specifically designed for financial domains, systematically identifying four canonical risk categories—e.g., semantic mismatch and misalignment with business objectives—that arise when combining automated metrics with SME judgment. It integrates SME input, multi-granularity metric analysis, formal risk modeling, and validation on real-world industrial use cases. Contribution/Results: The resulting multidimensional evaluation framework significantly improves assessment reliability and business alignment. Deployed across multiple financial institutions, it demonstrably reduces metric misuse risks in LLM deployment, thereby enhancing model trustworthiness and decision-making robustness.

Technology Category

Application Category

📝 Abstract
As Generative Artificial Intelligence is adopted across the financial services industry, a significant barrier to adoption and usage is measuring model performance. Historical machine learning metrics can oftentimes fail to generalize to GenAI workloads and are often supplemented using Subject Matter Expert (SME) Evaluation. Even in this combination, many projects fail to account for various unique risks present in choosing specific metrics. Additionally, many widespread benchmarks created by foundational research labs and educational institutions fail to generalize to industrial use. This paper explains these challenges and provides a Risk Assessment Framework to allow for better application of SME and machine learning Metrics
Problem

Research questions and friction points this paper is trying to address.

Assessing metric failure risks in financial LLMs
Addressing poor generalization of historical AI metrics
Providing risk framework for financial domain applications
Innovation

Methods, ideas, or system contributions that make the work stand out.

Risk assessment framework for LLM metric evaluation
Combining expert judgment with machine learning metrics
Tailoring metric selection to financial domain risks
W
William Flanagan
BNY Responsible AI Office
M
Mukunda Das
BNY AI Hub
R
Rajitha Ramanyake
BNY AI Hub
S
Swaunja Maslekar
BNY Responsible AI Office
M
Meghana Mangipudi
BNY AI Hub
J
Jeel Shah
BNY AI Hub
J
Joong Ho Choi
BNY AI Hub
S
Shruti Nair
BNY AI Hub
S
Shambhavi Bhusan
BNY Responsible AI Office
S
Sanjana Dulam
BNY AI Hub
M
Mouni Pendharkar
BNY Responsible AI Office
N
Nidhi Singh
BNY AI Hub
V
Vashisth Doshi
Carnegie Mellon University
S
Sachi Shah Paresh
Carnegie Mellon University