AI21 Labs Brings Generative AI to the Enterprise with Plug-and-Play Question Answering Engine that Eliminates Hallucinations

AI21 Labs, a leader in Generative AI and Large Language Models, launched today Contextual Answers, an plug-and-play engine that organizations can seamlessly embed into their digital assets to enhance the efficiency and accuracy of information queries with Generative AI. The engine provides businesses with LLM technology to instantaneously answer user questions about any organizational data.

According to a recent survey, 70% of enterprises are exploring Generative AI use, however 90% harbor concerns, including the risks related to the factual accuracy of generated content. One of the biggest risks in traditional Generative AI comes from hallucinations, or the tendency of many LLMs to falsify unknown responses. Contextual Answers offers increased reliability than existing models as it is engineered to only return fully accurate, relevant answers based on source documents that an organization chooses to upload, such as a help center library or an internal knowledgebase, preventing hallucinations.

Organizations can integrate Contextual Answers as an end-to-end solution that will only process data they upload, including financial reports, policies, or technical manuals. Furthermore, organizations don’t need to reformat uploaded documents. End-users, whether a business’ customers or internal employees, can use the feature to write any free-form question, such as “Can I download your app on Android?” or “ How do I file a lost employee card?” The model will deliver a concise answer from the context within an organization’s uploaded knowledgebase, saving the respective end-user from having to ask customer relations teams or managers.

Unlike when an organization works directly with an LLM, which can often be brittle, requiring engineers to do various practice prompts while also evaluating the model performance under different conditions, Contextual Answers can be implemented with no prior AI (machine learning or natural language processing) experience and with very little engineering knowledge. This makes implementing Contextual Answers faster and more cost efficient than a traditional solution.

There are no context windows, enabling organizations to upload unlimited data - hundreds of millions of documents - including technical manuals, financial reports, pharmaceutical records.   

This model has a deep understanding of language, supporting misspelling as well as missing words, conducting search queries despite grammatical errors. 

Contextual Answers has endless use cases, including: 

• Customer Support for CRMs and Independent Software Vendors: answering end user support questions using internal organization documentation, reducing the load and cost and improving customer satisfaction
• Financial Service Institutions: assisting in the analysis of business documents such as financial reports, call logs, and past presentations, allowing analysts to cover more resources 
• Education Service Providers: allowing students, teachers, and researchers to quickly find answers in large databases full of articles, books and research papers
• Legal Services and Insurance: providing the ability to quickly look up relevant legal documents, including legislation, regulations and internal compliance guidelines 
• Sales and Marketing: supporting sales associates by pulling information from product documents, competitor analysis, marketing materials, and sales playbooks to answer customer queries or build pitches
• Field Technicians: enabling field technicians to quickly reference manual specific questions without having to waste time searching through countless technical documents

AI21 Labs plans to embed this feature into Wordtune, its consumer platform to enhance and hasten writing and reading, allowing users to quickly retrieve select information from uploaded documents.

“There has been a lot of hype - and fear - surrounding Generative AI recently, with new exciting tools emerging daily and consumer demand through the roof. The initial fear around AI is starting to wane as the world realizes the benefits. McKinsey recently released a report estimating that AI will boost the world economy by trillions each year,” said Ori Goshen, Co-CEO and Co-Founder of AI21 Labs. “What we expect to happen over the second half of 2023 and into 2024 is that companies will get smarter about how to best implement AI into their respective workflows, and embrace the right tools, which is why we are so excited about the launch of Contextual Answers, further positioning us to serve as a key piece for any company’s AI strategy.”