Position: Standard Benchmarks Fail -- LLM Agents Present Overlooked Risks for Financial Applications

Zichen Chen, Jiaao Chen, Jianda Chen and Misha Sra

Papers from arXiv.org

Abstract: Current financial LLM agent benchmarks are inadequate. They prioritize task performance while ignoring fundamental safety risks. Threats like hallucinations, temporal misalignment, and adversarial vulnerabilities pose systemic risks in high-stakes financial environments, yet existing evaluation frameworks fail to capture these risks. We take a firm position: traditional benchmarks are insufficient to ensure the reliability of LLM agents in finance. To address this, we analyze existing financial LLM agent benchmarks, finding safety gaps and introducing ten risk-aware evaluation metrics. Through an empirical evaluation of both API-based and open-weight LLM agents, we reveal hidden vulnerabilities that remain undetected by conventional assessments. To move the field forward, we propose the Safety-Aware Evaluation Agent (SAEA), grounded in a three-level evaluation framework that assesses agents at the model level (intrinsic capabilities), workflow level (multi-step process reliability), and system level (integration robustness). Our findings highlight the urgent need to redefine LLM agent evaluation standards by shifting the focus from raw performance to safety, robustness, and real world resilience.

Date: 2025-02
New Economics Papers: this item is included in nep-inv
References: Add references at CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2502.15865 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2502.15865

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().