Flash Forward is a show about possible (and not so possible) future scenarios. What would the warranty on a sex robot look like? How would diplomacy work if we couldn’t lie? Could there ever be a fecal transplant black market? (Complicated, it wouldn’t, and yes, respectively, in case you’re curious.) Hosted and produced by award winning science journalist Rose Eveleth, each episode combines audio drama and journalism to go deep on potential tomorrows, and uncovers what those futures might re ...
…
continue reading
Player FM - Internet Radio Done Right
23 subscribers
Checked 1d ago
Added two years ago
Content provided by Arize AI. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Arize AI or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://staging.podcastplayer.com/legal.
Similar to Deep Papers
Big tech is transforming every aspect of our world. But how, and at what cost? This season of Land of the Giants – The Disney Dilemma – focuses on Disney’s ability to weather the ups and downs of the business cycle and changing tastes and explores what has kept it successful for over 100 years. The entertainment giant has leveraged nostalgia and its intellectual property to build a beloved brand, but after an acquisition spree that included Marvel, Lucasfilm, and 20th Century Fox, can it sus ...
…
continue reading
DNA science. Artificial intelligence. Smartphones and 3D printers. Science and technology have transformed the world we live in. But how did we get here? It wasn’t by accident. Well, sometimes it was. It was also the result of hard work, teamwork, and competition. And incredibly surprising moments. Hosted by bestselling author Steven Johnson (“How We Got To Now”), American Innovations uses immersive scenes to tell the stories of the scientists, engineers, and ordinary people behind the great ...
…
continue reading
We humans could have a bright future ahead of us that lasts billions of years. But we have to survive the next 200 years first. Join Josh Clark of Stuff You Should Know for a 10-episode deep dive that explores the future of humanity and finds dangers we have never encountered before lurking just ahead. And if we humans are alone in the universe, if we don't survive intelligent life dies out with us too.
…
continue reading
A myriad of AI, science, and technology experts explore the real challenges and enormous opportunities facing entrepreneurs who are building the future of health. Raising Health, a podcast by a16z Bio + Health and hosted by Kris Tatiossian and Olivia Webb, dives deep into the heart of biotechnology and healthcare innovation. Join veteran company builders, operators, and investors Vijay Pande, Julie Yoo, Vineeta Agarwala, and Jorge Conde, along with distinguished guests like Mark Cuban, Greg ...
…
continue reading
Come dive into one of the curiously delightful conversations overheard at National Geographic’s headquarters, as we follow explorers, photographers, and scientists to the edges of our big, weird, beautiful world. Hosted by Peter Gwin and Amy Briggs.
…
continue reading
The fun email marketing podcast. Sell more of your online courses, grow your membership and bring in more coaching clients with email marketing that doesn't stink. Sound good? Then join your fellow Email Marketing Heroes for your weekly dose of fun, practical, yet brutally honest email marketing advice. You can listen in to a piping hot, fresh episode every 'Email Marketing Wednesday' or if you prefer learning with your eyes instead of your ears, we turn each episode into a full written blog ...
…
continue reading
T
There’s a Better Way: Smart Talk on Healthcare and Technology
1
There’s a Better Way: Smart Talk on Healthcare and Technology
Surescripts
12k
30
The American healthcare system is one of the most innovative in the world. But it’s also riddled with complex challenges, such as access to affordable medications, inefficiency and administrative burdens, and communication barriers between providers. There’s clearly a better way—and at Surescripts, we have a unique sightline into what that may be. In this series, host Melanie Marcus, Chief Marketing Officer of Surescripts, sits down with today’s most inspiring and innovative leaders in healt ...
…
continue reading
Unseeable forces control human behavior and shape our ideas, beliefs, and assumptions. Invisibilia—Latin for invisible things—fuses narrative storytelling with science that will make you see your own life differently.
…
continue reading
Whether the topic is popcorn or particle physics, you can count on BrainStuff to explore -- and explain -- the everyday science in the world around us.
…
continue reading
Player FM - Podcast App
Go offline with the Player FM app!
Go offline with the Player FM app!
))
RAFT: Adapting Language Model to Domain Specific RAG
Manage episode 426158561 series 3448051
Content provided by Arize AI. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Arize AI or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
Where adapting LLMs to specialized domains is essential (e.g., recent news, enterprise private documents), we discuss a paper that asks how we adapt pre-trained LLMs for RAG in specialized domains. SallyAnn DeLucia is joined by Sai Kolasani, researcher at UC Berkeley’s RISE Lab (and Arize AI Intern), to talk about his work on RAFT: Adapting Language Model to Domain Specific RAG.
RAFT (Retrieval-Augmented FineTuning) is a training recipe that improves an LLM’s ability to answer questions in a “open-book” in-domain settings. Given a question, and a set of retrieved documents, the model is trained to ignore documents that don’t help in answering the question (aka distractor documents). This coupled with RAFT’s chain-of-thought-style response, helps improve the model’s ability to reason. In domain-specific RAG, RAFT consistently improves the model’s performance across PubMed, HotpotQA, and Gorilla datasets, presenting a post-training recipe to improve pre-trained LLMs to in-domain RAG.
Read it on the blog: https://arize.com/blog/raft-adapting-language-model-to-domain-specific-rag/
Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on LinkedIn and X.
49 episodes
ShareManage episode 426158561 series 3448051
Content provided by Arize AI. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Arize AI or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
Where adapting LLMs to specialized domains is essential (e.g., recent news, enterprise private documents), we discuss a paper that asks how we adapt pre-trained LLMs for RAG in specialized domains. SallyAnn DeLucia is joined by Sai Kolasani, researcher at UC Berkeley’s RISE Lab (and Arize AI Intern), to talk about his work on RAFT: Adapting Language Model to Domain Specific RAG.
RAFT (Retrieval-Augmented FineTuning) is a training recipe that improves an LLM’s ability to answer questions in a “open-book” in-domain settings. Given a question, and a set of retrieved documents, the model is trained to ignore documents that don’t help in answering the question (aka distractor documents). This coupled with RAFT’s chain-of-thought-style response, helps improve the model’s ability to reason. In domain-specific RAG, RAFT consistently improves the model’s performance across PubMed, HotpotQA, and Gorilla datasets, presenting a post-training recipe to improve pre-trained LLMs to in-domain RAG.
Read it on the blog: https://arize.com/blog/raft-adapting-language-model-to-domain-specific-rag/
Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on LinkedIn and X.
49 episodes
All episodes
×
D
Deep Papers
1 Scalable Chain of Thoughts via Elastic Reasoning 28:54
28:54 
Play Later 
Play Later 
Lists 
Like 
Liked28:54
Play Later Play Later Lists Like LikedIn this week's episode, we talk about Elastic Reasoning, a novel framework designed to enhance the efficiency and scalability of large reasoning models by explicitly separating the reasoning process into two distinct phases: thinking and solution . This separation allows for independent allocation of computational budgets, addressing challenges related to uncontrolled output lengths in real-world deployments with strict resource constraints. Our discussion explores how Elastic Reasoning contributes to more concise and efficient reasoning, even in unconstrained settings, and its implications for deploying LRMs in resource-limited environments. Read the paper here: https://arxiv.org/pdf/2505.05315 Sign up for the next discussion & see more AI research: arize.com/ai-research-papers Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Sleep-time Compute: Beyond Inference Scaling at Test-time 30:24
30:24 Play Later Play Later Lists Like Liked30:24
Play Later Play Later Lists Like LikedWhat if your LLM could think ahead —preparing answers before questions are even asked? In this week's paper read, we dive into a groundbreaking new paper from researchers at Letta, introducing sleep-time compute: a novel technique that lets models do their heavy lifting offline , well before the user query arrives. By predicting likely questions and precomputing key reasoning steps, sleep-time compute dramatically reduces test-time latency and cost—without sacrificing performance. We explore new benchmarks—Stateful GSM-Symbolic, Stateful AIME, and the multi-query extension of GSM—that show up to 5x lower compute at inference, 2.5x lower cost per query, and up to 18% higher accuracy when scaled. You’ll also see how this method applies to realistic agent use cases and what makes it most effective.If you care about LLM efficiency, scalability, or cutting-edge research. Explore more AI research, or sign up to hear the next session live: arize.com/ai-research-papers Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 LibreEval: The Largest Open Source Benchmark for RAG Hallucination Detection 27:19
27:19 Play Later Play Later Lists Like Liked27:19
Play Later Play Later Lists Like LikedFor this week's paper read, we actually 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. 📃 Read the paper: https://arize.com/llm-hallucination-dataset/ Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 AI Benchmark Deep Dive: Gemini 2.5 and Humanity's Last Exam 26:11
26:11 Play Later Play Later Lists Like Liked26:11
Play Later Play Later Lists Like LikedThis week we talk about modern AI benchmarks, taking a close look at Google's recent Gemini 2.5 release and its performance on key evaluations, notably Humanity's Last Exam (HLE). In the session we covered Gemini 2.5's architecture, its advancements in reasoning and multimodality, and its impressive context window. We also talked about how benchmarks like HLE and ARC AGI 2 help us understand the current state and future direction of AI. Read it on the blog: https://arize.com/blog/ai-benchmark-deep-dive-gemini-humanitys-last-exam/ Sign up to watch the next live recording: https://arize.com/resource/community-papers-reading/ Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
We cover Anthropic’s groundbreaking Model Context Protocol (MCP) . Though it was released in November 2024, we've been seeing a lot of hype around it lately, and thought it was well worth digging into. Learn how this open standard is revolutionizing AI by enabling seamless integration between LLMs and external data sources, fundamentally transforming them into capable, context-aware agents. We explore the key benefits of MCP, including enhanced context retention across interactions, improved interoperability for agentic workflows, and the development of more capable AI agents that can execute complex tasks in real-world environments. Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 AI Roundup: DeepSeek’s Big Moves, Claude 3.7, and the Latest Breakthroughs 30:23
30:23 Play Later Play Later Lists Like Liked30:23
Play Later Play Later Lists Like LikedThis week, we're mixing things up a little bit. Instead of diving deep into a single research paper, we cover the biggest AI developments from the past few weeks. We break down key announcements, including: DeepSeek’s Big Launch Week: A look at FlashMLA (DeepSeek’s new approach to efficient inference) and DeepEP (their enhanced pretraining method). Claude 3.7 & Claude Code: What’s new with Anthropic’s latest model, and what Claude Code brings to the AI coding assistant space. Stay ahead of the curve with this fast-paced recap of the most important AI updates. We'll be back next time with our regularly scheduled programming. Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 How DeepSeek is Pushing the Boundaries of AI Development 29:54
29:54 Play Later Play Later Lists Like Liked29:54
Play Later Play Later Lists Like LikedThis week, we dive into DeepSeek. SallyAnn DeLucia, Product Manager at Arize, and Nick Luzio, a Solutions Engineer, break down key insights on a model that have dominating headlines for its significant breakthrough in inference speed over other models. What’s next for AI (and open source)? From training strategies to real-world performance, here’s what you need to know. Read a summary: https://arize.com/blog/how-deepseek-is-pushing-the-boundaries-of-ai-development/ Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Multiagent Finetuning: A Conversation with Researcher Yilun Du 30:03
30:03 Play Later Play Later Lists Like Liked30:03
Play Later Play Later Lists Like LikedWe talk to Google DeepMind Senior Research Scientist (and incoming Assistant Professor at Harvard), Yilun Du, about his latest paper "Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains." This paper introduces a multiagent finetuning framework that enhances the performance and diversity of language models by employing a society of agents with distinct roles, improving feedback mechanisms and overall output quality. The method enables autonomous self-improvement through iterative finetuning, achieving significant performance gains across various reasoning tasks. It's versatile, applicable to both open-source and proprietary LLMs, and can integrate with human-feedback-based methods like RLHF or DPO, paving the way for future advancements in language model development. Read an overview on the blog Watch the full discussion Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Training Large Language Models to Reason in Continuous Latent Space 24:58
24:58 Play Later Play Later Lists Like Liked24:58
Play Later Play Later Lists Like LikedLLMs have typically been restricted to reason in the "language space," where chain-of-thought (CoT) is used to solve complex reasoning problems. But a new paper argues that language space may not always be the best for reasoning. In this paper read, we cover an exciting new technique from a team at Meta called Chain of Continuous Thought—also known as "Coconut." In the paper, "Training Large Language Models to Reason in a Continuous Latent Space" explores the potential of allowing LLMs to reason in an unrestricted latent space instead of being constrained by natural language tokens. Read a full breakdown of Coconut on our blog Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 LLMs as Judges: A Comprehensive Survey on LLM-Based Evaluation Methods 28:57
28:57 Play Later Play Later Lists Like Liked28:57
Play Later Play Later Lists Like LikedWe discuss a major survey of work and research on LLM-as-Judge from the last few years. "LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods" systematically examines the LLMs-as-Judge framework across five dimensions: functionality, methodology, applications, meta-evaluation, and limitations. This survey gives us a birds eye view of the advantages, limitations and methods for evaluating its effectiveness. Read a breakdown on our blog: https://arize.com/blog/llm-as-judge-survey-paper/ Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Merge, Ensemble, and Cooperate! A Survey on Collaborative LLM Strategies 28:47
28:47 Play Later Play Later Lists Like Liked28:47
Play Later Play Later Lists Like LikedLLMs have revolutionized natural language processing, showcasing remarkable versatility and capabilities. But individual LLMs often exhibit distinct strengths and weaknesses, influenced by differences in their training corpora. This diversity poses a challenge: how can we maximize the efficiency and utility of LLMs? A new paper, "Merge, Ensemble, and Cooperate: A Survey on Collaborative Strategies in the Era of Large Language Models," highlights collaborative strategies to address this challenge. In this week's episode, we summarize key insights from this paper and discuss practical implications of LLM collaboration strategies across three main approaches: merging, ensemble, and cooperation. We also review some new open source models we're excited about. Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Agent-as-a-Judge: Evaluate Agents with Agents 24:54
24:54 Play Later Play Later Lists Like Liked24:54
Play Later Play Later Lists Like LikedThis week, we break down the “Agent-as-a-Judge” framework—a new agent evaluation paradigm that’s kind of like getting robots to grade each other’s homework. Where typical evaluation methods focus solely on outcomes or demand extensive manual work, this approach uses agent systems to evaluate agent systems, offering intermediate feedback throughout the task-solving process. With the power to unlock scalable self-improvement, Agent-as-a-Judge could redefine how we measure and enhance agent performance. Let's get into it! Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
We break down OpenAI’s realtime API. Learn how to seamlessly integrate powerful language models into your applications for instant, context-aware responses that drive user engagement. Whether you’re building chatbots, dynamic content tools, or enhancing real-time collaboration, we walk through the API’s capabilities, potential use cases, and best practices for implementation. Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
D
Deep Papers
1 Swarm: OpenAI's Experimental Approach to Multi-Agent Systems 46:46
46:46 Play Later Play Later Lists Like Liked46:46
Play Later Play Later Lists Like LikedAs multi-agent systems grow in importance for fields ranging from customer support to autonomous decision-making, OpenAI has introduced Swarm, an experimental framework that simplifies the process of building and managing these systems. Swarm, a lightweight Python library, is designed for educational purposes, stripping away complex abstractions to reveal the foundational concepts of multi-agent architectures. In this podcast, we explore Swarm’s design, its practical applications, and how it stacks up against other frameworks. Whether you’re new to multi-agent systems or looking to deepen your understanding, Swarm offers a straightforward, hands-on way to get started. Read a Summary on the Blog Watch on YouTube Sign up for Upcoming Paper Readings Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
In this episode, we dive into the intriguing mechanics behind why chat experiences with models like GPT often start slow but then rapidly pick up speed. The key? The KV cache. This essential but under-discussed component enables the seamless and snappy interactions we expect from modern AI systems. Harrison Chu breaks down how the KV cache works, how it relates to the transformer architecture, and why it's crucial for efficient AI responses. By the end of the episode, you'll have a clearer understanding of how top AI products leverage this technology to deliver fast, high-quality user experiences. Tune in for a simplified explanation of attention heads, KQV matrices, and the computational complexities they present. Learn more about AI observability and evaluation , join the Arize AI Slack community or get the latest on LinkedIn and X .…
Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.
Similar to Deep Papers
Flash Forward is a show about possible (and not so possible) future scenarios. What would the warranty on a sex robot look like? How would diplomacy work if we couldn’t lie? Could there ever be a fecal transplant black market? (Complicated, it wouldn’t, and yes, respectively, in case you’re curious.) Hosted and produced by award winning science journalist Rose Eveleth, each episode combines audio drama and journalism to go deep on potential tomorrows, and uncovers what those futures might re ...
…
continue reading
Big tech is transforming every aspect of our world. But how, and at what cost? This season of Land of the Giants – The Disney Dilemma – focuses on Disney’s ability to weather the ups and downs of the business cycle and changing tastes and explores what has kept it successful for over 100 years. The entertainment giant has leveraged nostalgia and its intellectual property to build a beloved brand, but after an acquisition spree that included Marvel, Lucasfilm, and 20th Century Fox, can it sus ...
…
continue reading
DNA science. Artificial intelligence. Smartphones and 3D printers. Science and technology have transformed the world we live in. But how did we get here? It wasn’t by accident. Well, sometimes it was. It was also the result of hard work, teamwork, and competition. And incredibly surprising moments. Hosted by bestselling author Steven Johnson (“How We Got To Now”), American Innovations uses immersive scenes to tell the stories of the scientists, engineers, and ordinary people behind the great ...
…
continue reading
We humans could have a bright future ahead of us that lasts billions of years. But we have to survive the next 200 years first. Join Josh Clark of Stuff You Should Know for a 10-episode deep dive that explores the future of humanity and finds dangers we have never encountered before lurking just ahead. And if we humans are alone in the universe, if we don't survive intelligent life dies out with us too.
…
continue reading
A myriad of AI, science, and technology experts explore the real challenges and enormous opportunities facing entrepreneurs who are building the future of health. Raising Health, a podcast by a16z Bio + Health and hosted by Kris Tatiossian and Olivia Webb, dives deep into the heart of biotechnology and healthcare innovation. Join veteran company builders, operators, and investors Vijay Pande, Julie Yoo, Vineeta Agarwala, and Jorge Conde, along with distinguished guests like Mark Cuban, Greg ...
…
continue reading
Come dive into one of the curiously delightful conversations overheard at National Geographic’s headquarters, as we follow explorers, photographers, and scientists to the edges of our big, weird, beautiful world. Hosted by Peter Gwin and Amy Briggs.
…
continue reading
The fun email marketing podcast. Sell more of your online courses, grow your membership and bring in more coaching clients with email marketing that doesn't stink. Sound good? Then join your fellow Email Marketing Heroes for your weekly dose of fun, practical, yet brutally honest email marketing advice. You can listen in to a piping hot, fresh episode every 'Email Marketing Wednesday' or if you prefer learning with your eyes instead of your ears, we turn each episode into a full written blog ...
…
continue reading
T
There’s a Better Way: Smart Talk on Healthcare and Technology
1
There’s a Better Way: Smart Talk on Healthcare and Technology
Surescripts
12k30
The American healthcare system is one of the most innovative in the world. But it’s also riddled with complex challenges, such as access to affordable medications, inefficiency and administrative burdens, and communication barriers between providers. There’s clearly a better way—and at Surescripts, we have a unique sightline into what that may be. In this series, host Melanie Marcus, Chief Marketing Officer of Surescripts, sits down with today’s most inspiring and innovative leaders in healt ...
…
continue reading
Unseeable forces control human behavior and shape our ideas, beliefs, and assumptions. Invisibilia—Latin for invisible things—fuses narrative storytelling with science that will make you see your own life differently.
…
continue reading
Whether the topic is popcorn or particle physics, you can count on BrainStuff to explore -- and explain -- the everyday science in the world around us.
…
continue reading
Player FM - Podcast App
Go offline with the Player FM app!
Go offline with the Player FM app!
