Gleen AI desires to cease AI hallucinations utilizing enterprises’ personal information

As organizations world wide look to quickly consider, check, 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 keeping with Ashu Dubey, CEO and co-founder of Gleen, who spoke to VentureBeat solely in a video name interview.

As we speak, Gleen AI proclaims 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 information layer software program for enterprises, which is focused initially towards serving to them configure AI fashions to supply buyer assist.

The issue with hallucinations

Generative AI instruments resembling the favored, commercially obtainable massive language fashions (LLMs) resembling ChatGPT, Claude 2, LLaMA 2, Bard, and others, are skilled to reply to human-entered prompts and queries by producing information that has been related to the phrases and concepts the human person has entered.

However the gen AI fashions don’t at all times get it proper, and in lots of circumstances, produce info that’s inaccurate or not related however that the mannequin’s coaching has related beforehand with one thing the human person has stated.

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

Whereas these inaccurate responses will be at occasions humorous or attention-grabbing, for companies making an attempt to depend on them to provide correct information for workers or customers, the outcomes will be vastly dangerous — particularly for highly-regulated, life-and-death info in healthcare, drugs, heavy business, and others.

What Gleen does to stop hallucinations

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

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

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

Gleen’s layer does the next:

1. Aggregates structured and unstructured enterprise data 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 stated this “permits us to glean the sign from the noise.” (Additionally the origin of Gleen’s title.)
3. Constructs a data graph to know relationships between entities. The graph aids in retrieving probably the most related info for a given question.
4. Checks the LLM’s response towards the curated info earlier than delivering the output. If proof is missing, the chatbot will say “I don’t know” somewhat than danger hallucination.

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

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

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

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

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

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

“LLMs will hallucinate when not given sufficient related info to floor the response,” stated 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 facet,” stated Estevan Vilar, group assist at Matter Labs, an organization devoted to creating the cryptocurrency Ethereum extra enterprise pleasant. “We simply offered a couple of hyperlinks, and the remaining was clean.”

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

As extra corporations look to faucet into the ability of LLMs whereas mitigating their downsides, Gleen AI’s accuracy layer could 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 could have an AI assistant powered by their very own proprietary data graph,” stated Dubey. “This vector database will change into as vital of an asset as their web site, enabling customized automation throughout your entire buyer lifecycle.”