FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios

• URL: http://arxiv.org/abs/2605.00706v1
• Date: Fri, 01 May 2026 14:51:24 GMT
• Title: FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
• Abstract summary: Large language models (LLMs) are increasingly applied in financial scenarios.<n>They may produce harmful outputs, including facilitating illegal activities or unethical behavior.<n>We propose FinSafetyBench, a benchmark designed to test an LLM's refusal of requests that violate financial compliance.
• Score: 20.47244088110227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly applied in financial scenarios. However, they may produce harmful outputs, including facilitating illegal activities or unethical behavior, posing serious compliance risks. To systematically evaluate LLM safety in finance, we propose FinSafetyBench, a bilingual (English-Chinese) red-teaming benchmark designed to test an LLM's refusal of requests that violate financial compliance. Grounded in real-world financial crime cases and ethics standards, the benchmark comprises 14 subcategories spanning financial crimes and ethical violations. Through extensive experiments on general-purpose and finance-specialized LLMs under three representative attack settings, we identify critical vulnerabilities that allow adversarial prompts to bypass compliance safeguards. Further analysis reveals stronger susceptibility in Chinese contexts and highlights the limitations of prompt-level defenses against sophisticated or implicit manipulation strategies.

Related papers

• FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming [11.54323482443491]
  Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks.<n>We introduce FinRED, an expert-guided red-teaming framework for financial safety evaluation developed with financial experts.<n>FinRED uses a novel two-level taxonomy mapping global standards to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline.
  arXiv  Detail & Related papers  (2026-06-18T07:46:18Z)
• FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments [29.19862712902908]
  FinVault is the first execution-grounded security benchmark for financial agents.<n>We show that existing defense mechanisms remain ineffective in realistic financial agent settings.
  arXiv  Detail & Related papers  (2026-01-09T03:25:45Z)
• Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection [64.75447949495307]
  Large language models (LLMs) have been widely applied across various domains of finance.<n> behavioral biases can lead to instability and uncertainty in decision-making.<n>mfmdscen is a benchmark for evaluating behavioral biases in mfmd across diverse economic scenarios.
  arXiv  Detail & Related papers  (2026-01-08T22:00:32Z)
• FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain [54.06289302468199]
  FinTrust is a benchmark specifically designed for evaluating the trustworthiness of LLMs in finance applications.<n> proprietary models like o4-mini outperforms in most tasks such as safety.<n>Open-source models like DeepSeek-V3 have advantage in specific areas like industry-level fairness.
  arXiv  Detail & Related papers  (2025-10-17T01:45:49Z)
• Uncovering the Vulnerability of Large Language Models in the Financial Domain via Risk Concealment [29.36824550283463]
  Large Language Models (LLMs) are increasingly integrated into financial applications, yet existing red-teaming research primarily targets harmful content.<n>We introduce Risk-Concealment Attacks (RCA), a novel multi-turn framework that iteratively conceals regulatory risks to provoke seemingly compliant yet regulatory-violating responses.<n>Experiments on FIN-Bench demonstrate that RCA effectively bypasses nine mainstream LLMs, achieving an average attack success rate (ASR) of 93.18%, including 98.28% on GPT-4.1 and 97.56% on OpenAI o1.
  arXiv  Detail & Related papers  (2025-09-07T22:35:15Z)
• Standard Benchmarks Fail - Auditing LLM Agents in Finance Must Prioritize Risk [31.43947127076459]
  Standard benchmarks fixate on how well large language model (LLM) agents perform in finance, yet say little about whether they are safe to deploy.<n>We argue that accuracy metrics and return-based scores provide an illusion of reliability, overlooking vulnerabilities such as hallucinated facts, stale data, and adversarial prompt manipulation.
  arXiv  Detail & Related papers  (2025-02-21T12:56:15Z)
• Chat Bankman-Fried: an Exploration of LLM Alignment in Finance [4.892013668424246]
  As jurisdictions enact legislation on AI safety, the concept of alignment must be defined and measured.<n>This paper proposes an experimental framework to assess whether large language models (LLMs) adhere to ethical and legal standards in the relatively unexplored context of finance.
  arXiv  Detail & Related papers  (2024-11-01T08:56:17Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models [61.324062412648075]
  CFinBench is an evaluation benchmark for assessing the financial knowledge of large language models (LLMs) under Chinese context. It comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%.
  arXiv  Detail & Related papers  (2024-07-02T14:34:36Z)
• SuperCLUE-Fin: Graded Fine-Grained Analysis of Chinese LLMs on Diverse Financial Tasks and Applications [17.34850312139675]
  SC-Fin is a pioneering evaluation framework tailored for Chinese-native financial large language models (FLMs) It assesses FLMs across six financial application domains and twenty-five specialized tasks. Using multi-turn, open-ended conversations that mimic real-life scenarios, SC-Fin measures models on a range of criteria.
  arXiv  Detail & Related papers  (2024-04-29T19:04:35Z)
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
  ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
  arXiv  Detail & Related papers  (2024-04-06T15:01:47Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• Safety Assessment of Chinese Large Language Models [51.83369778259149]
  Large language models (LLMs) may generate insulting and discriminatory content, reflect incorrect social values, and may be used for malicious purposes. To promote the deployment of safe, responsible, and ethical AI, we release SafetyPrompts including 100k augmented prompts and responses by LLMs.
  arXiv  Detail & Related papers  (2023-04-20T16:27:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.