Zoom의 통합 AI 접근 방식을 통해 Zoom에서 가장 인기 있는 기능에서 가장 우수한 품질 제공

In November 2023, I shared how Zoom’s federated AI approach achieved quality nearly equal to OpenAI GPT-4 with only 6% of the inference cost. As impressive as those results were, we can now deliver even better AI quality compared to OpenAI’s GPT-4 for our most popular meeting features. Zoom AI Companion reduced relative errors by over 20% (for Zoom meeting summary’s “recaps”) and 60% (for “next steps”) in comparison to GPT-4 in our internal human-validated blind benchmarking. 

In support of our training efforts to refine task completion quality, our unique federated approach to AI takes advantage of many closed- and open-source advanced large language models (LLMs) working together for better results. This is in contrast to other providers who are tied to specific LLMs. For example, Microsoft Copilot has relied on GPT-4 and Google has relied on Gemini.

This approach to AI sets Zoom AI Companion apart, providing our customers with a high-quality experience with our most popular features. As I shared in my last update, we use our proprietary Z-scorer to judge the quality of our AI-generated outputs. First, we employ a lower-cost LLM most suitable for each task. Then, our Z-scorer evaluates the quality of the initial task completion. If needed, we can use another complementary LLM to refine the task. This process results in a higher-quality output in the same way a team of people can accomplish more together than any one individual.

We’ve since improved our Z-scorer by incorporating additional quality signals from a variety of LLMs. Also, to better align with human preference, we improved federated reinforcement learning. By federating Zoom LLM in combination with a set of complementary LLMs, Zoom’s popular meeting summary delivers high-quality results and, according to our recent benchmarking, can now outperform GPT-4, which is used to power Copilot in Microsoft Teams.

Regarding AI safety, we also reduced the inherent bias in most LLMs by forming a committee composed of multiple LLMs such as Claude-3, Gemini, and GPT-4 to reduce hallucinations and improve our Zoom LLM. For example, different LLMs are unlikely to make the same hallucinated mistake, so we can derive more consistent responses and reduce the impact of outliers. 

최근 회의 요약의 가장 인기 있는 두 가지 기능인 미팅 개요와 다음 단계에 대한 벤치마킹 조사를 진행했습니다. 2023년 9월 AI Companion 출시 이후 50만 명이 넘는 Zoom 고객이 이 기능을 사용했습니다. 

최근 내부 벤치마킹 조사에서는 심사원에게 각 요약본을 생성하는 데 사용된 AI 모델을 공개하지 않은 상태에서 가장 정확한 회의 요약을 선택하도록 요청했습니다. 아래 차트에서 볼 수 있듯이, 각 블라인드 테스트에서 Zoom LLM의 미팅 개요와 다음 단계 추출 기능이 모두 GPT-4(영어)보다 뛰어난 것으로 나타났습니다. Zoom은 미팅 개요와 미팅 다음 단계의 상대적 오류를 각각 20%, 60% 이상 줄일 수 있으며, 이는 곧 더 우수한 품질을 제공하는 것을 의미합니다.

또한 Zoom LLM을 사용하여 일본어로 작성된 전체 회의 요약의 품질을 GPT-4와 비교하여 측정했습니다. 아래 차트에서 볼 수 있듯이, Zoom의 통합 접근 방식이 여기서 더 나은 결과를 가져올 수 있었습니다. 

We’re committed to bringing the benefits of Zoom AI Companion across the Zoom platform to our customers at no additional cost on eligible paid Zoom plans.* This relentless focus on AI quality drives higher customer value in Zoom Workplace and Zoom Business Services. In addition, according to a GigaOm study commissioned by Zoom (published March 26, 2024), AI Companion transcription performed at 95% accuracy, and for in-meeting questions scenarios, AI Companion delivered results that are four times faster than ChatGPT-4 web.

With these latest innovations, you can feel confident that every Zoom meeting can be accompanied by an AI-generated meeting summary that has some of the best AI quality in the industry. 

• Learn how Zoom AI Companion can fit into your work.
• To turn on and use Zoom AI Companion, visit our getting started guide.
• If you don’t have an eligible paid Zoom plan, upgrade today to access the benefits of AI Companion. 

*AI Companion may not be available for all regions or industry verticals.