As organizations all over the world look to rapidly evaluate, test, and deploy generative AI into their workflows — both on the backend, front-end (customer-facing) or each — many decision-makers stay rightfully involved about a number of the lingering points, amongst them, the issue of AI hallucinations.

However a brand new startup, Gleen AI, has burst on the scene and claims to “resolve hallucination,” in response to Ashu Dubey, CEO and co-founder of Gleen, who spoke to VentureBeat solely in a video name interview.

As we speak, Gleen AI declares a $4.9 million funding spherical from Sluggish Ventures, sixth Man Ventures, South Park Commons, Spartan Group, and different enterprise companies and angel buyers together with former Fb/Meta Platforms’ VP of product administration Sam Lessin, to proceed constructing out its anti-hallucination knowledge layer software program for enterprises, which is focused initially towards serving to them configure AI fashions to offer buyer assist.

The issue with hallucinations

Generative AI instruments reminiscent of the favored, commercially out there massive language fashions (LLMs) reminiscent of ChatGPT, Claude 2, LLaMA 2, Bard, and others, are skilled to answer human-entered prompts and queries by producing knowledge that has been related to the phrases and concepts the human consumer has entered.

However the gen AI fashions don’t all the time get it proper, and in lots of circumstances, produce data that’s inaccurate or not related however that the mannequin’s coaching has related beforehand with one thing the human consumer has mentioned.

One good latest instance, ChatGPT making an attempt to reply “when has the Earth eclipsed Mars?” and offering a convincing sounding clarification that’s totally inaccurate (the very premise of the query is flawed and inaccurate — the Earth can’t eclipse Mars).

Whereas these inaccurate responses could be at instances humorous or attention-grabbing, for companies making an attempt to depend on them to provide correct knowledge for workers or customers, the outcomes could be massively dangerous — particularly for highly-regulated, life-and-death data in healthcare, drugs, heavy trade, and others.

What Gleen does to stop hallucinations

“What we do is, after we ship knowledge [from a user] to an LLM, we give info that may create reply,” Dubey mentioned. “If we don’t imagine we have now sufficient info, we gained’t ship the information to the LLM.”

Particularly, Gleen has created proprietary AI and machine studying (ML) layer impartial of no matter LLM that their enterprise buyer desires to deploy.

This layer securely sifts by way of and enterprise’s personal inside knowledge, turning it right into a vector database, and makes use of this knowledge enhance the standard of the the AI mannequin’s solutions.

Gleen’s layer does the next:

1. Aggregates structured and unstructured enterprise information from a number of sources like assist documentation, FAQs, product specs, manuals, wikis, boards and previous chat logs.
2. Curates and extracts key info, eliminating noise and redundancy. Dubey mentioned this “permits us to glean the sign from the noise.” (Additionally the origin of Gleen’s title.)
3. Constructs a information graph to know relationships between entities. The graph aids in retrieving essentially the most related info for a given question.
4. Checks the LLM’s response in opposition to the curated info earlier than delivering the output. If proof is missing, the chatbot will say “I don’t know” slightly than danger hallucination.

The AI layer acts as a checkpoint, cross-checking the LLM’s response earlier than it’s delivered to the top consumer. This eliminates the danger of the chatbot offering false or fabricated data. It’s like having a top quality management supervisor for chatbots.

“We solely have interaction the LLM when we have now excessive confidence the info are complete,” Dubey defined. “In any other case we’re clear that extra data is required from the consumer.”

Gleen’s software program additionally allows customers to shortly create customer-support chatbots for his or her clients, and alter their “persona” relying on the use-case.

Gleen’s answer is AI model-agonistic, and might assist any of the a number of main fashions on the market which have utility programming interface (API) integrations.

For these clients wanting the most well-liked LLM, it helps OpenAI’s GPT-3.5 Turbo mannequin. For these involved about knowledge being despatched to the LLM host firm, it additionally helps LLaMA 2 run on the corporate’s personal servers (although OpenAI has repeatedly mentioned it doesn’t acquire or use buyer knowledge to coach its fashions, besides when the shopper expressly permits it).

For some security-sensitive clients, Gleen affords the choice to make use of a proprietary LLM that by no means touches the open web. However Dubey believes LLMs themselves should not the supply of hallucination.

“LLMs will hallucinate when not given sufficient related info to floor the response,” mentioned Dubey. “Our accuracy layer solves that by controlling the inputs to the LLM.”

Early suggestions is promising

Proper now, the top results of a buyer utilizing Gleen is a customized chatbot that may be plugged into their very own Slack or surfaced as an end-user dealing with assist agent.

Gleen AI is already being utilized by clients spanning quantum computing, crypto and different technical domains the place accuracy is paramount.

“Implementing Gleen AI was near no effort on our aspect,” mentioned Estevan Vilar, neighborhood assist at Matter Labs, an organization devoted to creating the cryptocurrency Ethereum extra enterprise pleasant. “We simply supplied just a few hyperlinks, and the remaining was easy.”

Gleen is providing potential clients a free “AI playground” the place they’ll create their very own customized chatbot utilizing their firm’s knowledge.

As extra corporations look to faucet into the facility of LLMs whereas mitigating their downsides, Gleen AI’s accuracy layer might supply them the trail to deploying generative AI on the degree of accuracy they and their clients demand.

“Our imaginative and prescient is each firm can have an AI assistant powered by their very own proprietary information graph,” mentioned Dubey. “This vector database will turn into as essential of an asset as their web site, enabling personalised automation throughout your entire buyer lifecycle.”