Bloomberg AI Researchers Mitigate Risks of “Unsafe” RAG LLMs and GenAI in Finance

There's immense pressure for companies in every industry to adopt AI, but not everyone has the in-house expertise, tools, or resources to understand where and how to deploy AI responsibly. Bloomberg hopes this taxonomy – when combined with red teaming and guardrail systems – helps to responsibly enable the financial industry to develop safe and reliable GenAI systems, be compliant with evolving regulatory standards and expectations, as well as strengthen trust among clients.
Bloomberg AI Researchers Mitigate Risks of "Unsafe" RAG LLMs and GenAI in Finance

Two new academic papers reflect Bloomberg’s commitment to transparent, trustworthy, and responsible AI


From discovering that retrieval augmented generation (RAG)-based large language models (LLMs) are less “safe” to introducing an AI content risk taxonomy meeting the unique needs of GenAI systems in financial services, researchers across Bloomberg’s AI Engineering group, Data AI group, and CTO Office aim to help organizations deploy more trustworthy solutions.

They have published two new academic papers that have significant implications for how organizations deploy GenAI systems more safely and responsibly, particularly in high-stakes domains like capital markets financial services.

In RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models,” Bloomberg researchers found that RAG, a widely-used technique that integrates context from external data sources to enhance the accuracy of LLMs, can actually make models less “safe” and their outputs less reliable.

To determine whether RAG-based LLMs are safer than their non-RAG counterparts, the authors used more than 5,000 harmful questions to assess the safety profiles of 11 popular LLMs, including Claude-3.5-Sonnet, Llama-3-8B, Gemma-7B, and GPT-4o. Comparing the resulting behaviors across 16 safety categories, the findings demonstrate that there were large increases in unsafe responses under the RAG setting. In particular, they discovered that even very “safe” models, which refused to answer nearly all harmful queries in the non-RAG setting, become more vulnerable in the RAG setting [see Figure 3 from the paper].

The change of risk profile from non-RAG to RAG is model dependent. (Figure 3, RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models, arXiv, 2025.)

This research clearly underscores the need for anyone using RAG LLMs to assess whether their models have any hidden layers of vulnerability and what additional safeguards they might need to add.

“This counterintuitive finding has far-reaching implications given how ubiquitously RAG is used in GenAI applications such as customer support agents and question-answering systems. The average Internet user interacts with RAG-based systems daily,” explained Dr. Amanda Stent, Bloomberg’s Head of AI Strategy & Research in the Office of the CTO. “AI practitioners need to be thoughtful about how to use RAG responsibly, and what guardrails are in place to ensure outputs are appropriate. Our research offers a framework for approaching that so others can evaluate their own solutions and identify any potential blind spots.”

In a related paper, “Understanding and Mitigating Risks of Generative AI in Financial Services,” Bloomberg’s researchers examined how GenAI is being used in capital markets financial services and found that existing general purpose safety taxonomies and guardrail systems fail to account for domain-specific risks.

To close this gap, they introduced a new AI content risk taxonomy that meets the needs of real-world GenAI systems for financial services. It goes beyond what may be addressed by general-purpose safety taxonomies and guardrail systems by addressing risks specific to the financial sector such as confidential disclosure, counterfactual narrative, financial services impartiality, and financial services misconduct.

“There have been strides in academic research addressing toxicity, bias, fairness, and related safety issues for GenAI applications for a broad consumer audience, but there has been significantly less focus on GenAI in industry applications, particularly in financial services,” said David Rabinowitz, Technical Product Manager for AI Guardrails at Bloomberg.

[See Table 1 from the paper]

The categories in Bloomberg’s AI content safety taxonomy for financial services. (Table 1, Understanding and Mitigating Risks of Generative AI in Financial Services, 2025.)

“There’s immense pressure for companies in every industry to adopt AI, but not everyone has the in-house expertise, tools, or resources to understand where and how to deploy AI responsibly,” said Dr. Sebastian Gehrmann, Bloomberg’s Head of Responsible AI. “Bloomberg hopes this taxonomy – when combined with red teaming and guardrail systems – helps to responsibly enable the financial industry to develop safe and reliable GenAI systems, be compliant with evolving regulatory standards and expectations, as well as strengthen trust among clients.”

The RAG safety paper will be presented at the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025) in Albuquerque, New Mexico later this week. The AI risk taxonomy paper will be presented at the ACM Conference on Fairness, Accountability, and Transparency (FAccT) in Athens, Greece in June. For more details, read the Tech At Bloomberg blog post and both papers:

About AI at Bloomberg
Since 2009, Bloomberg has been building and using artificial intelligence (AI) in the finance domain – including machine learning (ML), natural language processing (NLP), information retrieval (IR), time-series analysis, and generative models – to help process and organize the ever-increasing volume of structured and unstructured financial information. With this technology, Bloomberg is developing new ways for financial professionals and business leaders to derive valuable intelligence and actionable insights from high-quality financial information and make more informed business decisions. Learn more about Bloomberg’s AI solutions at www.bloomberg.com/AIatBloomberg.

About Bloomberg
Bloomberg is a global leader in business and financial information, delivering trusted data, news, and insights that bring transparency, efficiency, and fairness to markets. The company helps connect influential communities across the global financial ecosystem via reliable technology solutions that enable our customers to make more informed decisions and foster better collaboration. For more information, visit Bloomberg.com/company or request a demo.


Recent Content

The future of manufacturing is intelligent, autonomous, and sustainable. Powered by private 5G networks, AI, and digital twins, smart factories are revolutionizing how goods are produced and maintained. From predictive maintenance to immersive virtual twins and AI-optimized energy systems, smart manufacturing is unlocking new levels of efficiency and innovation across industries—from ports and shipyards to agriculture and healthcare.
Smart mobility is reshaping how the world moves, powered by 5G, AI, and edge computing. From autonomous vehicles and real-time logistics to AI-driven drones and connected public transport, intelligent transportation systems are redefining urban mobility, logistics, and industrial automation. As global investment and collaboration grow, the transportation industry is transforming into a $11.1 trillion smart ecosystem focused on sustainability, efficiency, and connectivity.
FinTech, private 5G networks, and AI are converging to reshape digital finance across industries. From embedded payments and super apps to AI-driven credit scoring and secure M2M transactions, this $2 trillion opportunity is powered by mobile technology, cloud infrastructure, and regulatory evolution. Leaders must act fast to unlock new revenue, scale inclusion, and secure digital ecosystems.
The future of sports and entertainment is fan-first, immersive, and data-driven. Powered by D2C models, 5G networks, AI content creation, and super apps, industry leaders are reimagining fan experiences—from Bundesliga’s mobile strategy to Web2.5’s tokenized communities. The shift is not just technical but cultural, prioritizing personalization, monetization, and real-time interaction across every touchpoint.
Satellite-mobile convergence is rapidly shifting from niche to mainstream, enabling global mobile coverage through Non-Terrestrial Networks (NTN). With direct-to-device (D2D) standards now supported by 3GPP Releases 17–19, traditional mobile phones can connect directly to satellites. This development has unlocked use cases in emergency response, smart agriculture, logistics, and IoT—paving the way for a future where 6G, edge AI, and multi-orbit architectures redefine connectivity. Learn how telecoms, enterprises, and regulators are navigating the path to a fully connected planet.
NVIDIA and Google Cloud are collaborating to bring secure, on-premises agentic AI to enterprises by integrating Google’s Gemini models with NVIDIA’s Blackwell platforms. Leveraging confidential computing and enhanced infrastructure like the GKE Inference Gateway and Triton Inference Server, the partnership ensures scalable AI deployment without compromising regulatory compliance or data sovereignty.
Whitepaper
Download the 5G Assurance Operator Survey conducted on behalf of RADCOM by TeckNexus. Get the viewpoint from the 5G operators' operational team....
Radcom Logo

It seems we can't find what you're looking for.

Download Magazine

With Subscription

Subscribe To Our Newsletter

Scroll to Top