Our Approach to AI
We’re committed to innovation
Bloomberg Tax has been at the forefront of innovation and tax information delivery since 1959 – providing fast access to news, expert insights, and tools that help tax professionals turn knowledge into action.
We believe in serving our customers with unparalleled industry expertise alongside state-of-the-art technology. Our business is built on technology that makes our vast collection of tax information searchable, discoverable, and actionable.
With more than a decade of experience in applying AI to tax information and workflows, we continue to develop new ways for our customers to make data-driven decisions while saving time and resources.
AI overview for Bloomberg Tax
As a leading content and technology service provider to the tax industry, Bloomberg Tax continues to create smarter, more focused AI-enhanced applications for our customers. This includes increasing the relevancy of results in searches, surfacing deep insights from analysis of millions of documents, serving up-to-the-minute news, generating answers, and providing document drafting support.
As there continues to be an exponential increase in tax information, sophisticated AI techniques help us deliver the most important insights you need.
Our success in building AI-enhanced solutions is due to our dedication in four key areas:
- Expertise and accuracy
- Customer-centric approach
- Transparency you can trust
- Differentiated content
Expertise and accuracy
As an affiliate of Bloomberg L.P., we have access to deep professional experience in the field of AI. Bloomberg Industry Group utilizes hundreds of AI researchers and engineers who are constantly exploring state-of-the-art AI tools and technologies to determine how to apply them in the tax domain.
In addition to building and deploying AI models in the company’s solutions, these researchers and engineers also publish multiple research papers each year, putting us at the forefront of AI research and the deployment of AI solutions. As a result of this work, and with the emergence and proliferation of generative AI, we are uniquely positioned to understand both its power and limitations, so we can build safeguards that foster accuracy in our AI models.
In fact, many of our engineers have worked on Bloomberg Tax for over a decade, developing deep domain expertise. Their understanding of the tax domain enables them to understand our customers’ problems and apply the appropriate technology to solving them.
For our customers, two realities are often in conflict: accuracy is essential, but much of their decision-making is based on interpretations of nuanced laws, regulations, codes, opinions, and more.
Our approach to ensuring accuracy in our generative AI tools is equally thorough. We know generative AI can be inconsistent – hallucinations, inaccuracies, and lack of context are all things we work to avoid and correct in our generative AI offerings.
We utilize the industry-standard retrieval-augmented generation (RAG) framework, as well as our proprietary guardrail service that leverages our foundational technology, deep legal domain expertise, and content to ensure an AI-generated content is grounded in our original content or primary source materials, not the internet at large.
We also have an extensive benchmarking process and system. With the help of tax professionals, we evaluate the accuracy of our generative AI at all phases – from development and early internal testing to the beta environment and customer testing, and onward throughout the life of the product. With these guardrails in place, we’re able to continuously tune and fix the model to prevent it from drifting over time or answers becoming less accurate.
Customer-centric approach
It’s in our DNA to be obsessed with providing our customers with cutting-edge technology built on a foundation of trusted news and analysis that makes them more efficient, more effective, and more knowledgeable about the issues that matter most.
When we build AI-powered tools, our primary focus is whether they will actually solve our customers’ challenges. We understand that adopting new technologies and new workflows can be disruptive, costly, and time consuming. Our mission is to reduce friction and create a natural, incremental transition to using AI.
Rather than developing technology that will upend a customer’s entire workflow or create the end work product, we have taken a building-block approach that focuses on addressing one specific task at a time and seamlessly integrating into existing processes. Collectively, these efficiencies add up to a user-empowered workstream with a low barrier to entry.
We want our AI to make your job easier – not do it for you.
One example of this is Bloomberg Tax’s AI Lab, where we develop new AI tools through partnerships with our customers. This allows real users to provide feedback and have direct input on what challenges we address, which solutions we build and how they function, and the degree to which they interact with AI in our product.
When interacting with our generative AI experiments, customers can provide immediate feedback to help us fine tune our models, ensure accuracy, and fit within their desired workflow.
As always, Bloomberg Tax will continue to collaborate with our customers and empower them to drive the direction of our product development to best serve their needs.
Transparency you can trust
At Bloomberg Tax, we believe that transparency is the key ingredient to building trust in our AI.
We are committed to providing our customers with clear documentation of:
- Where and when our products employ generative AI
- The sources used by our AI
- The benchmarking and validation process for our AI
Throughout our history of employing AI in our products, we have never left a user guessing about where information is coming from. For example, our tools that have traditional used machine learning to suggest related content will indicate why that content is being suggested. Likewise, when generative AI provides an answer or suggests text, it includes links to source material and/or an explanation of why it returned that result.
While we understand the power of generative AI, we also recognize its limitations. AI-generated responses are never 100% trustworthy and pose the risk of hallucinations. We do our best to mitigate these risks by beta testing all generative AI tools before releasing them. In addition, our AI doesn’t generate answers on its own – it also looks through our large collection of carefully vetted information to enhance the accuracy and reliability of the responses it provides. In fact, Bloomberg Tax will abstain from answering when there is no available content covering the topic in question or when the search query is outside the tax scope.
Our brains and expertise are still needed as part of the equation, so we advise all our customers to validate the responses with primary sources and to use their best judgment.
Differentiated content
Bloomberg Tax’s cutting-edge AI technology is built on a foundation of:
- Comprehensive primary and secondary sources
- Award-winning unbiased news
- Expert analysis
- Time-saving workflow tools
This trove of authoritative content is constantly expanding, including our database of 500,000+ agency guidance or determination documents and our collection of 500+ practitioner-written Tax Management Portfolios that grows to cover new issues as they arise.
Our large language models are training on this specialized content, and every answer they provide is sourced from expert-vetted materials. AI is also applied to this massive collection of information to improve discoverability and allow users to find precisely what they’re looking for in less time.
AI in our products
The use of AI makes our content more discoverable, delivers answers and insights to our customers, and unlocks connections across millions of documents to lead users to useful information they might not have considered or found otherwise.
Bloomberg Tax provides access to information and analytics on various content sets, including:
- 500,000 agency guidance documents or determinations
- 500+ in-depth Tax Management Portfolios
- 23,000 tax treaties
To make this mountain of information useful, Bloomberg Tax is enhanced by several AI applications that help customers maximize efficiency and uncover important, actionable insights.
We leverage AI – including machine learning (ML), natural language processing (NLP), information retrieval (IR), recommendation systems, and large language models (LLM) – to help process and organize the ever-increasing volume of information needed to work more quickly and efficiently.
Bloomberg Tax uses AI in four areas:
- Extraction
- Search
- Summarization
- Syntax generation
Extraction
Machine learning and natural language processing algorithms are used to read various documents – including statutes, regulations, Portfolios, and guidance – and extract semantic meaning from them. Extracting and normalizing such information with accuracy and low latency requires training, fine-tuning, and then optimizing for speed.
AI is essential to the collection of information that impacts our customers’ tax planning, compliance, and provision activities.
For example, we constantly monitor more than 2,000 state tax department websites across the U.S. to collect, normalize, analyze, and summarize tax developments to help users make informed decisions on their tax strategies.
Search
With the help of AI, you can find the information you need within the wide variety of news, analysis, and additional primary and secondary sources that Bloomberg Tax provides. AI enables us to deliver a comprehensive search experience for the entire platform, allowing you to easily discover what is particularly relevant to you.
Users can simply type phrases or ask questions in natural language to search across all resources. Our AI also supports the use of traditional Boolean search structure, as we know a portion of our users prefer it. Search results will provide the information you want or point you to resources where you can do deeper research to find the answer.
Summarization
To help speed up your tax research, Bloomberg Tax’s AI condenses the most important information into short, easy-to-absorb answers. This approach enables you to quickly understand key themes and points within a large volume of documents or instantly identify applicable tax rules without having to search manually.
For example, Bloomberg Tax generates a response or summary to your question or keyword utilizing primary and secondary source documents. The feature also provides citations and links to supporting authorities and source documents that were used when generating the answer.
This feature is also accessible within Bloomberg Tax Workpapers, allowing users to source tax rates, citation descriptions, and simplified summaries of complex content without having to switch to the research product.
Syntax generation
Our AI Expression Generator is a feature within Bloomberg Tax Workpapers that enables users to use plain English to describe their data transformation needs and generate usable syntax for the filter or formula blocks.
For example, a user can describe a desired formula as “take the lesser of amount and total” and our AI will provide the working formula to manipulate the data in Bloomberg Tax Workpapers.