LibreEval: The Largest Open Source Benchmark for RAG Hallucination Detection

Deep Papers

Player FM - Internet Radio Done Right

29 subscribers

اضافه شده در two سال پیش

محتوای ارائه شده توسط Arize AI. تمام محتوای پادکست شامل قسمت‌ها، گرافیک‌ها و توضیحات پادکست مستقیماً توسط Arize AI یا شریک پلتفرم پادکست آن‌ها آپلود و ارائه می‌شوند. اگر فکر می‌کنید شخصی بدون اجازه شما از اثر دارای حق نسخه‌برداری شما استفاده می‌کند، می‌توانید روندی که در اینجا شرح داده شده است را دنبال کنید.https://fa.player.fm/legal

TED Tech

1
How AI is saving billions of years of human research time | Max Jaderberg 19:15

21 weeks پیش19:15

پخش در آینده

لیست ها

پسندیدن

دوست داشته شد

19:15

Can AI compress the years long research time of a PhD into seconds? Research scientist Max Jaderberg explores how “AI analogs” simulate real-world lab work with staggering speed and scale, unlocking new insights on protein folding and drug discovery. Drawing on his experience working on Isomorphic Labs' and Google DeepMind's AlphaFold 3 — an AI model for predicting the structure of molecules — Jaderberg explains how this new technology frees up researchers' time and resources to better understand the real, messy world and tackle the next frontiers of science, medicine and more. For a chance to give your own TED Talk, fill out the Idea Search Application: ted.com/ideasearch . Interested in learning more about upcoming TED events? Follow these links: TEDNext: ted.com/futureyou TEDAI Vienna: ted.com/ai-vienna Hosted on Acast. See acast.com/privacy for more information.…

حدود یک سال پیش 27:19

MP3•خانه قسمت

For this week's paper read, we dive into our own research.
We wanted to create a replicable, evolving dataset that can keep pace with model training so that you always know you're testing with data your model has never seen before. We also saw the prohibitively high cost of running LLM evals at scale, and have used our data to fine-tune a series of SLMs that perform just as well as their base LLM counterparts, but at 1/10 the cost.
So, over the past few weeks, the Arize team generated the largest public dataset of hallucinations, as well as a series of fine-tuned evaluation models.
We talk about what we built, the process we took, and the bottom line results. You can read the recap of LibreEval here. Dive into the research, or sign up to join us next time.

Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on LinkedIn and X.

52 قسمت

#Science #Tech #Math #Business #Arize AI

Deep Papers