Be a part of our day by day and weekly newsletters for the newest updates and unique content material on industry-leading AI protection. Study Extra
Contextual AI unveiled its grounded language mannequin (GLM) at the moment, claiming it delivers the best factual accuracy within the {industry} by outperforming main AI programs from Google, Anthropic and OpenAI on a key benchmark for truthfulness.
The startup, based by the pioneers of retrieval-augmented technology (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 massive language fashions have remodeled enterprise software program, factual inaccuracies — typically known as hallucinations — stay a vital problem for enterprise adoption. Contextual AI goals to unravel this by making a mannequin particularly optimized for enterprise RAG functions the place accuracy is paramount.
“We knew that a part of the answer could be a way known as RAG — retrieval-augmented technology,” mentioned Douwe Kiela, CEO and cofounder of Contextual AI, in an unique interview with VentureBeat. “And we knew that as a result of RAG is initially my concept. What this firm is about is absolutely about doing RAG the appropriate manner, to type of the following stage of doing RAG.”
The corporate’s focus differs considerably from general-purpose fashions like ChatGPT or Claude, that are designed to deal with all the things from inventive writing to technical documentation. Contextual AI as a substitute targets high-stakes enterprise environments the place factual precision outweighs inventive flexibility.
“In case you have a RAG downside and also you’re in an enterprise setting in a extremely regulated {industry}, you haven’t any tolerance in anyway for hallucination,” defined Kiela. “The identical general-purpose language mannequin that’s helpful for the advertising and marketing division will not be what you need in an enterprise setting the place you might be rather more delicate to errors.”
How Contextual AI makes ‘groundedness’ the brand new gold normal for enterprise language fashions
The idea of “groundedness” — making certain AI responses stick strictly to data explicitly supplied within the context — has emerged as a vital requirement for enterprise AI programs. In regulated industries like finance, healthcare and telecommunications, corporations 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: “In case you give a recipe or a method to a normal language mannequin, and someplace in it, you say, ‘however that is solely true for many instances,’ most language fashions are nonetheless simply going to provide the recipe assuming it’s true. However our language mannequin says, ‘Really, it solely says that that is true for many instances.’ It’s capturing this extra little bit of nuance.”
The power to say “I don’t know” is an important one for enterprise settings. “Which is known as a very highly effective characteristic, if you consider it in an enterprise setting,” Kiela added.
Contextual AI’s RAG 2.0: A extra built-in solution 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 makes use of a frozen off-the-shelf mannequin for embeddings, a vector database for retrieval, and a black-box language mannequin for technology, stitched collectively via prompting or an orchestration framework,” in line with an organization assertion. “This results in a ‘Frankenstein’s monster’ of generative AI: the person parts technically work, however the entire is way from optimum.”
As a substitute, Contextual AI collectively optimizes all parts of the system. “Now we have this mixture-of-retrievers element, which is known as a solution to do clever retrieval,” Kiela defined. “It seems on the query, after which it thinks, primarily, like a lot of the newest technology of fashions, it thinks, [and] first it plans a method for doing a retrieval.”
This whole system works in coordination with what Kiela calls “one of the best re-ranker on the earth,” 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 technology, Contextual AI’s platform has lately added assist for multimodal content material together with charts, diagrams and structured knowledge from common platforms like BigQuery, Snowflake, Redshift and Postgres.
“Probably the most difficult issues in enterprises are on the intersection of unstructured and structured knowledge,” Kiela famous. “What I’m largely enthusiastic about is absolutely this intersection of structured and unstructured knowledge. Many of the actually thrilling issues in massive enterprises are smack bang on the intersection of structured and unstructured, the place you’ve gotten some database data, some transactions, perhaps some coverage paperwork, perhaps a bunch of different issues.”
The platform already helps a wide range of advanced visualizations, together with circuit diagrams within the semiconductor {industry}, 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 Elementary AI Analysis (FAIR) group and Hugging Face, Contextual AI has secured clients together with HSBC, Qualcomm and the Economist. The corporate positions itself as serving to enterprises lastly understand concrete returns on their AI investments.
“That is actually a chance for corporations who’re perhaps beneath stress to begin delivering ROI from AI to begin extra specialised options that truly clear up their issues,” Kiela mentioned. “And a part of that basically is having a grounded language mannequin that’s perhaps a bit extra boring than a normal language mannequin, however it’s actually good at ensuring that it’s grounded within the context and that you may actually belief it to do its job.”
