Monday, 12 Jan 2026
Subscribe
logo
  • Global
  • AI
  • Cloud Computing
  • Edge Computing
  • Security
  • Investment
  • Sustainability
  • More
    • Colocation
    • Quantum Computing
    • Regulation & Policy
    • Infrastructure
    • Power & Cooling
    • Design
    • Innovations
    • Blog
Font ResizerAa
Data Center NewsData Center News
Search
  • Global
  • AI
  • Cloud Computing
  • Edge Computing
  • Security
  • Investment
  • Sustainability
  • More
    • Colocation
    • Quantum Computing
    • Regulation & Policy
    • Infrastructure
    • Power & Cooling
    • Design
    • Innovations
    • Blog
Have an existing account? Sign In
Follow US
© 2022 Foxiz News Network. Ruby Design Company. All Rights Reserved.
Data Center News > Blog > AI > Small models as paralegals: LexisNexis distills models to build AI assistant
AI

Small models as paralegals: LexisNexis distills models to build AI assistant

Last updated: March 21, 2025 12:14 pm
Published March 21, 2025
Share
Small models as paralegals: LexisNexis distills models to build AI assistant
SHARE

Be part of our each day and weekly newsletters for the newest updates and unique content material on industry-leading AI protection. Study Extra


When authorized analysis firm LexisNexis created its AI assistant Protégé, it needed to determine the easiest way to leverage its experience with out deploying a big mannequin. 

Protégé goals to assist legal professionals, associates and paralegals write and proof authorized paperwork and be certain that something they cite in complaints and briefs is correct. Nonetheless, LexisNexis didn’t desire a normal authorized AI assistant; they needed to construct one which learns a agency’s workflow and is extra customizable. 

LexisNexis noticed the chance to deliver the ability of enormous language fashions (LLMs) from Anthropic and Mistral and discover the perfect fashions that reply consumer questions the perfect, Jeff Riehl, CTO of LexisNexis Authorized and Skilled, advised VentureBeat.

“We use the perfect mannequin for the precise use case as a part of our multi-model method. We use the mannequin that gives the perfect outcome with the quickest response time,” Riehl mentioned. “For some use circumstances, that will probably be a small language mannequin like Mistral or we carry out distillation to enhance efficiency and cut back price.”

Whereas LLMs nonetheless present worth in constructing AI functions, some organizations flip to utilizing small language fashions (SLMs) or distilling LLMs to turn out to be small variations of the identical mannequin. 

Distillation, the place an LLM “teaches” a smaller mannequin, has turn out to be a preferred methodology for a lot of organizations. 

Small fashions usually work finest for apps like chatbots or easy code completion, which is what LexisNexis needed to make use of for Protégé. 

See also  $42.1 million poured into startup offering energy-efficient solutions for costly and unwieldy operational data and AI workloads

This isn’t the primary time LexisNexis constructed AI functions, even earlier than launching its authorized analysis hub LexisNexis + AI in July 2024.

“We have now used a whole lot of AI previously, which was extra round pure language processing, some deep studying and machine studying,” Riehl mentioned. “That basically modified in November 2022 when ChatGPT was launched, as a result of previous to that, a whole lot of the AI capabilities had been form of behind the scenes. However as soon as ChatGPT got here out, the generative capabilities, the conversational capabilities of it was very, very intriguing to us.”

Small, fine-tuned fashions and mannequin routing 

Riehl mentioned LexisNexis makes use of totally different fashions from a lot of the main mannequin suppliers when constructing its AI platforms. LexisNexis + AI used Claude fashions from Anthropic, OpenAI’s GPT fashions and a mannequin from Mistral. 

This multimodal method helped break down every process customers needed to carry out on the platform. To do that, LexisNexis needed to architect its platform to change between fashions. 

“We’d break down no matter process was being carried out into particular person elements, after which we might determine the perfect massive language mannequin to assist that element. One instance of that’s we are going to use Mistral to evaluate the question that the consumer entered in,” Riehl mentioned. 

For Protégé, the corporate needed sooner response instances and fashions extra fine-tuned for authorized use circumstances. So it turned to what Riehl calls “fine-tuned” variations of fashions, primarily smaller weight variations of LLMs or distilled fashions. 

See also  Virtus to build new Saunderton data center campus to meet AI, cloud demands

“You don’t want GPT-4o to do the evaluation of a question, so we use it for extra subtle work, and we change fashions out,” he mentioned. 

When a consumer asks Protégé a query a couple of particular case, the primary mannequin it pings is a fine-tuned Mistral “for assessing the question, then figuring out what the aim and intent of that question is” earlier than switching to the mannequin finest suited to finish the duty. Riehl mentioned the following mannequin may very well be an LLM that generates new queries for the search engine or one other mannequin that summarizes outcomes. 

Proper now, LexisNexis largely depends on a fine-tuned Mistral mannequin although Riehl mentioned it used a fine-tuned model of Claude “when it first got here out; we’re not utilizing it within the product as we speak however in different methods.” LexisNexis can also be fascinated about utilizing different OpenAI fashions particularly for the reason that firm got here out with new reinforcement fine-tuning capabilities final 12 months. LexisNexis is within the technique of evaluating OpenAI’s reasoning fashions together with o3 for its platforms. 

Riehl added that it might additionally have a look at utilizing Gemini fashions from Google. 

LexisNexis backs all of its AI platforms with its personal data graph to carry out retrieval augmented technology (RAG) capabilities, particularly as Protégé might assist launch agentic processes later. 

The AI authorized suite

Even earlier than the appearance of generative AI, LexisNexis examined the potential for placing chatbots to work within the authorized {industry}. In 2017, the corporate examined an AI assistant that will compete with IBM’s Watson-powered Ross and Protégé sits within the firm’s LexisNexis + AI platform, which brings collectively the AI companies of LexisNexis. 

See also  Astrolight Raises €2.8M to Build Optical Space-Earth Data Highway

Protégé helps regulation corporations with duties that paralegals or associates are inclined to do. It helps write authorized briefs and complaints which might be grounded in corporations’ paperwork and knowledge, counsel authorized workflow subsequent steps, counsel new prompts to refine searches, draft questions for depositions and discovery, hyperlink quotes in filings for accuracy, generate timelines and, after all, summarize advanced authorized paperwork. 

“We see Protégé because the preliminary step in personalization and agentic capabilities,” Riehl mentioned. “Take into consideration the various kinds of legal professionals: M&A, litigators, actual property. It’s going to proceed to get increasingly personalised based mostly on the precise process you do. Our imaginative and prescient is that each authorized skilled may have a private assistant to assist them do their job based mostly on what they do, not what different legal professionals do.”

Protégé now competes towards different authorized analysis and expertise platforms. Thomson Reuters personalized OpenAI’s o1-mini-model for its CoCounsel authorized assistant. Harvey, which raised $300 million from buyers together with LexisNexis, additionally has a authorized AI assistant. 


Source link
TAGGED: assistant, Build, distills, LexisNexis, models, paralegals, small
Share This Article
Twitter Email Copy Link Print
Previous Article Leadership change at Green Mountain Leadership change at Green Mountain
Next Article BuildOps Raises $127M in Series C Funding BuildOps Raises $127M in Series C Funding
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Your Trusted Source for Accurate and Timely Updates!

Our commitment to accuracy, impartiality, and delivering breaking news as it happens has earned us the trust of a vast audience. Stay ahead with real-time updates on the latest events, trends.
FacebookLike
TwitterFollow
InstagramFollow
YoutubeSubscribe
LinkedInFollow
MediumFollow
- Advertisement -
Ad image

Popular Posts

New figures show record investment in British AI companies

New figures present that backing for British AI firms reached report ranges final 12 months,…

September 4, 2025

A lollipop interface for simulating taste in virtual environments

A possible software state of affairs of the style interface programs in blended actuality. Credit…

November 26, 2024

How data centres could help power their local community

Kevin Stickney, Managing Director at Erda Vitality, believes that the time has come to flip…

April 15, 2025

H2 2025 – Data Centre Review

To offer the perfect experiences, we use applied sciences like cookies to retailer and/or entry…

October 26, 2025

Microsoft Neocloud Deals Cross $60B in Spending Spree

(Bloomberg) -- Microsoft Corp. has dedicated greater than $60 billion to neocloud knowledge heart corporations,…

November 5, 2025

You Might Also Like

Autonomy without accountability: The real AI risk
AI

Autonomy without accountability: The real AI risk

By saad
The future of personal injury law: AI and legal tech in Philadelphia
AI

The future of personal injury law: AI and legal tech in Philadelphia

By saad
How AI code reviews slash incident risk
AI

How AI code reviews slash incident risk

By saad
From cloud to factory – humanoid robots coming to workplaces
AI

From cloud to factory – humanoid robots coming to workplaces

By saad
Data Center News
Facebook Twitter Youtube Instagram Linkedin

About US

Data Center News: Stay informed on the pulse of data centers. Latest updates, tech trends, and industry insights—all in one place. Elevate your data infrastructure knowledge.

Top Categories
  • Global Market
  • Infrastructure
  • Innovations
  • Investments
Usefull Links
  • Home
  • Contact
  • Privacy Policy
  • Terms & Conditions

© 2024 – datacenternews.tech – All rights reserved

Welcome Back!

Sign in to your account

Lost your password?
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.
You can revoke your consent any time using the Revoke consent button.