Contextual AI unveiled its grounded language mannequin (GLM) at the moment, claiming it delivers the very best factual accuracy within the trade by outperforming main AI methods from Google, Anthropic and OpenAI on a key benchmark for truthfulness.
The startup, based by the pioneers of retrieval-augmented era (RAG) expertise, reported that its GLM achieved an 88% factuality rating on the FACTS benchmark, in comparison with 84.6% for Google’s Gemini 2.0 Flash, 79.4% for Anthropic’s Claude 3.5 Sonnet and 78.8% for OpenAI’s GPT-4o.
Whereas giant language fashions have reworked enterprise software program, factual inaccuracies — typically referred to as hallucinations — stay a important problem for enterprise adoption. Contextual AI goals to resolve this by making a mannequin particularly optimized for enterprise RAG functions the place accuracy is paramount.
“We knew that part of the solution would be a technique called RAG — retrieval-augmented generation,” mentioned Douwe Kiela, CEO and cofounder of Contextual AI, in an unique interview with VentureBeat. “And we knew that because RAG is originally my idea. What this company is about is really about doing RAG the right way, to kind of the next level of doing RAG.”
The corporate’s focus differs considerably from general-purpose fashions like ChatGPT or Claude, that are designed to deal with every little thing from artistic writing to technical documentation. Contextual AI as an alternative targets high-stakes enterprise environments the place factual precision outweighs artistic flexibility.
“If you have a RAG problem and you’re in an enterprise setting in a highly regulated industry, you have no tolerance whatsoever for hallucination,” defined Kiela. “The same general-purpose language model that is useful for the marketing department is not what you want in an enterprise setting where you are much more sensitive to mistakes.”
A benchmark comparability displaying Contextual AI’s new grounded language mannequin (GLM) outperforming opponents from Google, Anthropic and OpenAI on factual accuracy exams. The corporate claims its specialised method reduces AI hallucinations in enterprise settings.(Credit score: Contextual AI)
How Contextual AI makes ‘groundedness’ the brand new gold customary for enterprise language fashions
The idea of “groundedness” — guaranteeing AI responses stick strictly to data explicitly supplied within the context — has emerged as a important requirement for enterprise AI methods. In regulated industries like finance, healthcare and telecommunications, firms want AI that both delivers correct data or explicitly acknowledges when it doesn’t know one thing.
Kiela supplied an instance of how this strict groundedness works: “If you give a recipe or a formula to a standard language model, and somewhere in it, you say, ‘but this is only true for most cases,’ most language models are still just going to give you the recipe assuming it’s true. But our language model says, ‘Actually, it only says that this is true for most cases.’ It’s capturing this additional bit of nuance.”
The flexibility to say “I don’t know” is an important one for enterprise settings. “Which is really a very powerful feature, if you think about it in an enterprise setting,” Kiela added.
Contextual AI’s RAG 2.0: A extra built-in approach to course of firm data
Contextual AI’s platform is constructed on what it calls “RAG 2.0,” an method that strikes past merely connecting off-the-shelf parts.
“A typical RAG system uses a frozen off-the-shelf model for embeddings, a vector database for retrieval, and a black-box language model for generation, stitched together through prompting or an orchestration framework,” in line with an organization assertion. “This leads to a ‘Frankenstein’s monster’ of generative AI: the individual components technically work, but the whole is far from optimal.”
As an alternative, Contextual AI collectively optimizes all parts of the system. “We have this mixture-of-retrievers component, which is really a way to do intelligent retrieval,” Kiela defined. “It looks at the question, and then it thinks, essentially, like most of the latest generation of models, it thinks, [and] first it plans a strategy for doing a retrieval.”
This whole system works in coordination with what Kiela calls “the best re-ranker in the world,” which helps prioritize probably the most related data earlier than sending it to the grounded language mannequin.
Past plain textual content: Contextual AI now reads charts and connects to databases
Whereas the newly introduced GLM focuses on textual content era, Contextual AI’s platform has lately added assist for multimodal content material together with charts, diagrams and structured information from widespread platforms like BigQuery, Snowflake, Redshift and Postgres.
“The most challenging problems in enterprises are at the intersection of unstructured and structured data,” Kiela famous. “What I’m mostly excited about is really this intersection of structured and unstructured data. Most of the really exciting problems in large enterprises are smack bang at the intersection of structured and unstructured, where you have some database records, some transactions, maybe some policy documents, maybe a bunch of other things.”
The platform already helps quite a lot of advanced visualizations, together with circuit diagrams within the semiconductor trade, in line with Kiela.
Contextual AI’s future plans: Creating extra dependable instruments for on a regular basis enterprise
Contextual AI plans to launch its specialised re-ranker element shortly after the GLM launch, adopted by expanded document-understanding capabilities. The corporate additionally has experimental options for extra agentic capabilities in improvement.
Based in 2023 by Kiela and Amanpreet Singh, who beforehand labored at Meta’s Basic AI Analysis (FAIR) crew and Hugging Face, Contextual AI has secured prospects together with HSBC, Qualcomm and the Economist. The corporate positions itself as serving to enterprises lastly understand concrete returns on their AI investments.
“This is really an opportunity for companies who are maybe under pressure to start delivering ROI from AI to start looking at more specialized solutions that actually solve their problems,” Kiela mentioned. “And part of that really is having a grounded language model that is maybe a bit more boring than a standard language model, but it’s really good at making sure that it’s grounded in the context and that you can really trust it to do its job.”
Day by day insights on enterprise use instances with VB Day by day
If you wish to impress your boss, VB Day by day has you lined. We provide the inside scoop on what firms are doing with generative AI, from regulatory shifts to sensible deployments, so you possibly can share insights for optimum ROI.
An error occured.
