Be part of our day by day and weekly newsletters for the most recent updates and unique content material on industry-leading AI protection. Be taught Extra
When authorized analysis firm LexisNexis created its AI assistant Protégé, it wished to determine one of the best ways to leverage its experience with out deploying a big mannequin.
Protégé goals to assist attorneys, 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 basic authorized AI assistant; they wished to construct one which learns a agency’s workflow and is extra customizable.
LexisNexis noticed the chance to deliver the facility of enormous language fashions (LLMs) from Anthropic and Mistral and discover one of the best fashions that reply person questions one of the best, Jeff Reihl, CTO of LexisNexis Authorized and Skilled, informed VentureBeat.
“We use one of the best mannequin for the precise use case as a part of our multi-model strategy. We use the mannequin that gives one of the best outcome with the quickest response time,” Reihl mentioned. “For some use instances, that will probably be a small language mannequin like Mistral or we carry out distillation to enhance efficiency and cut back value.”
Whereas LLMs nonetheless present worth in constructing AI purposes, some organizations flip to utilizing small language fashions (SLMs) or distilling LLMs to develop into small variations of the identical mannequin.
Distillation, the place an LLM “teaches” a smaller mannequin, has develop into a well-liked technique for a lot of organizations.
Small fashions typically work finest for apps like chatbots or easy code completion, which is what LexisNexis wished to make use of for Protégé.
This isn’t the primary time LexisNexis constructed AI purposes, even earlier than launching its authorized analysis hub LexisNexis + AI in July 2024.
“Now we have used plenty of AI up to now, which was extra round pure language processing, some deep studying and machine studying,” Reihl mentioned. “That basically modified in November 2022 when ChatGPT was launched, as a result of previous to that, plenty of the AI capabilities have been sort 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
Reihl 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 strategy helped break down every activity customers wished 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 activity was being carried out into particular person parts, after which we might determine one of the best giant language mannequin to assist that element. One instance of that’s we are going to use Mistral to evaluate the question that the person entered in,” Reihl mentioned.
For Protégé, the corporate wished sooner response instances and fashions extra fine-tuned for authorized use instances. So it turned to what Reihl calls “fine-tuned” variations of fashions, basically smaller weight variations of LLMs or distilled fashions.
“You don’t want GPT-4o to do the evaluation of a question, so we use it for extra subtle work, and we swap fashions out,” he mentioned.
When a person asks Protégé a query a few 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. Reihl mentioned the subsequent mannequin could possibly 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 Reihl mentioned it used a fine-tuned model of Claude “when it first got here out; we’re not utilizing it within the product in the present day however in different methods.” LexisNexis can also be excited by utilizing different OpenAI fashions particularly because the 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.
Reihl added that it could additionally have a look at utilizing Gemini fashions from Google.
LexisNexis backs all of its AI platforms with its personal information graph to carry out retrieval augmented era (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 might 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.
Protégé helps legislation companies with duties that paralegals or associates are likely to do. It helps write authorized briefs and complaints which can be grounded in companies’ paperwork and information, recommend authorized workflow subsequent steps, recommend new prompts to refine searches, draft questions for depositions and discovery, hyperlink quotes in filings for accuracy, generate timelines and, in fact, summarize advanced authorized paperwork.
“We see Protégé because the preliminary step in personalization and agentic capabilities,” Reihl mentioned. “Take into consideration the several types of attorneys: M&A, litigators, actual property. It’s going to proceed to get increasingly more customized based mostly on the precise activity you do. Our imaginative and prescient is that each authorized skilled could have a private assistant to assist them do their job based mostly on what they do, not what different attorneys do.”
Protégé now competes in opposition to different authorized analysis and know-how 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
