Source link : https://tech365.info/when-correct-ai-remains-to-be-dangerously-incomplete/
Usually, when constructing, coaching and deploying AI, enterprises prioritize accuracy. And that, little question, is necessary; however in extremely advanced, nuanced industries like regulation, accuracy alone isn’t sufficient. Larger stakes imply greater requirements: Fashions outputs should be assessed for relevancy, authority, quotation accuracy and hallucination charges.
To sort out this immense activity, LexisNexis has developed past customary retrieval-augmented era (RAG) to graph RAG and agentic graphs; it has additionally constructed out “planner” and “reflection” AI brokers that parse requests and criticize their very own outputs.
“There’s no such [thing] as ‘perfect AI’ because you never get 100% accuracy or 100% relevancy, especially in complex, high stake domains like legal,” Min Chen, LexisNexis’ SVP and chief AI officer, acknowledges in a brand new VentureBeat Past the Pilot podcast.
The objective is to handle that uncertainty as a lot as potential and translate it into constant buyer worth. “At the end of the day, what matters most for us is the quality of the AI outcome, and that is a continuous journey of experimentation, iteration and improvement,” Chen stated.
Getting ‘complete’ solutions to multi-faceted questions
To guage fashions and their outputs, Chen’s workforce has established greater than a half-dozen “sub metrics” to measure “usefulness” based mostly on a number of components — authority, quotation…
—-
Author : tech365
Publish date : 2026-02-18 18:18:00
Copyright for syndicated content belongs to the linked Source.
—-
1 – 2 – 3 – 4 – 5 – 6 – 7 – 8