Deep Papers

For this paper read, we’re joined by Samuel Marks, Postdoctoral Research Associate at Northeastern University, to discuss his paper, “The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False Datasets.” Samuel and his team curated high-quality datasets of true/false statements and used them to study in detail the structure of LLM representations of truth. Overall, they present evidence that language models linearly represent the truth or falsehood of factual statements and also introduce a novel technique, mass-mean probing, which generalizes better and is more causally implicated in model outputs than other probing techniques.Find the transcript and read more here: https://arize.com/blog/the-geometry-of-truth-emergent-linear-structure-in-llm-representation-of-true-false-datasets-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

In this paper read, we discuss “Towards Monosemanticity: Decomposing Language Models Into Understandable Components,” a paper from Anthropic that addresses the challenge of understanding the inner workings of neural networks, drawing parallels with the complexity of human brain function. It explores the concept of “features,” (patterns of neuron activations) providing a more interpretable way to dissect neural networks. By decomposing a layer of neurons into thousands of features, this approach uncovers hidden model properties that are not evident when examining individual neurons. These features are demonstrated to be more interpretable and consistent, offering the potential to steer model behavior and improve AI safety.Find the transcript and more here: https://arize.com/blog/decomposing-language-models-with-dictionary-learning-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

We discuss RankVicuna, the first fully open-source LLM capable of performing high-quality listwise reranking in a zero-shot setting. While researchers have successfully applied LLMs such as ChatGPT to reranking in an information retrieval context, such work has mostly been built on proprietary models hidden behind opaque API endpoints. This approach yields experimental results that are not reproducible and non-deterministic, threatening the veracity of outcomes that build on such shaky foundations. RankVicuna provides access to a fully open-source LLM and associated code infrastructure capable of performing high-quality reranking.Find the transcript and more here: https://arize.com/blog/rankvicuna-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Join Arize Co-Founder & CEO Jason Lopatecki, and ML Solutions Engineer, Sally-Ann DeLucia, as they discuss “Explaining Grokking Through Circuit Efficiency." This paper explores novel predictions about grokking, providing significant evidence in favor of its explanation. Most strikingly, the research conducted in this paper demonstrates two novel and surprising behaviors: ungrokking, in which a network regresses from perfect to low test accuracy, and semi-grokking, in which a network shows delayed generalization to partial rather than perfect test accuracy.Find the transcript and more here: https://arize.com/blog/explaining-grokking-through-circuit-efficiency-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning.  In this episode, we discuss the paper, “Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior.” This episode is led by SallyAnn Delucia (ML Solutions Engineer, Arize AI), and Amber Roberts (ML Solutions Engineer, Arize AI).  The research they discuss highlights that while LLMs have great generalization capabilities, they struggle to effectively predict and optimize communication to get the desired receiver behavior. We’ll explore whether this might be because of a lack of “behavior tokens” in LLM training corpora and how Large Content Behavior Models (LCBMs) might help to solve this issue.Find the transcript and more here: https://arize.com/blog/large-content-and-behavior-models-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. In this paper reading, we explore the paper ‘Skeleton-of-Thought’ (SoT) approach, aimed at reducing large language model latency while enhancing answer quality. This episode is led by Aparna Dhinakaran ( Chief Product Officer, Arize AI) and Sally-Ann Delucia (ML Solutions Engineer, Arize AI), with two of the paper authors: Xuefei Ning, Postdoctoral Researcher at Tsinghua University and Zinan Lin, Senior Researcher, Microsoft Research. SoT’s innovative methodology guides LLMs to construct answer skeletons before parallel content elaboration, achieving impressive speed-ups of up to 2.39x across 11 models. Don’t miss the opportunity to delve into this human-inspired optimization strategy and its profound implications for efficient and high-quality language generation.Full transcript and more here: https://arize.com/blog/skeleton-of-thought-llms-can-do-parallel-decoding-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. This episode is led by Aparna Dhinakaran ( Chief Product Officer, Arize AI) and Michael Schiff (Chief Technology Officer, Arize AI), as they discuss the paper "Llama 2: Open Foundation and Fine-Tuned Chat Models."In this paper reading, we explore the paper “Developing Llama 2: Pretrained Large Language Models Optimized for Dialogue.” The paper introduces Llama 2, a collection of pretrained and fine-tuned large language models ranging from 7 billion to 70 billion parameters. Their fine-tuned model, Llama 2-Chat, is specifically designed for dialogue use cases and showcases superior performance on various benchmarks. Through human evaluations for helpfulness and safety, Llama 2-Chat emerges as a promising alternative to closed-source models. Discover the approach to fine-tuning and safety improvements, allowing us to foster responsible development and contribute to this rapidly evolving field.Full transcript and more here: https://arize.com/blog/llama-2-open-foundation-and-fine-tuned-chat-models-paper-reading/Follow AI__Pub on Twitter. To learn more about ML observability,  join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. This episode is led by Sally-Ann DeLucia and Amber Roberts, as they discuss the paper "Lost in the Middle: How Language Models Use Long Contexts." This paper examines how well language models utilize longer input contexts. The study focuses on multi-document question answering and key-value retrieval tasks. The researchers find that performance is highest when relevant information is at the beginning or end of the context. Accessing information in the middle of long contexts leads to significant performance degradation. Even explicitly long-context models experience decreased performance as the context length increases. The analysis enhances our understanding and offers new evaluation protocols for future long-context models. Full transcript and more here: https://arize.com/blog/lost-in-the-middle-how-language-models-use-long-contexts-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Hosted by AI Pub creator Brian Burns and Arize AI founders Jason Lopatecki and Aparna Dhinakaran, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning.In this episode, we talk about Orca. Recent research focuses on improving smaller models through imitation learning using outputs from large foundation models (LFMs). Challenges include limited imitation signals, homogeneous training data, and a lack of rigorous evaluation, leading to overestimation of small model capabilities. To address this, Orca is a 13-billion parameter model that learns to imitate LFMs’ reasoning process. Orca leverages rich signals from GPT-4, surpassing state-of-the-art models by over 100% in complex zero-shot reasoning benchmarks. It also shows competitive performance in professional and academic exams without CoT. Learning from step-by-step explanations, generated by humans or advanced AI models, enhances model capabilities and skills.Full transcript and more here: https://arize.com/blog/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4-paper-reading/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Hosted by AI Pub creator Brian Burns and Arize AI founders Jason Lopatecki and Aparna Dhinakaran, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. In this episode, we interview Timo Schick and Thomas Scialom, the Research Scientists at Meta AI behind Toolformer. "Vanilla" language models cannot access information about the external world. But what if we gave language models access to calculators, question-answer search, and other APIs to generate more powerful and accurate output? Further, how do we train such a model? How can we automatically generate a dataset of API-call-annotated text at internet scale, without human labeling?Timo and Thomas give a step-by-step walkthrough of building and training Toolformer, what motivated them to do it, and what we should expect in the next generation of tool-LLM powered products.Follow AI__Pub on Twitter. To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Hosted by AI Pub creator Brian Burns and Arize AI founders Jason Lopatecki and Aparna Dhinakaran, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. In this episode, we interview Dan Fu and Tri Dao, inventors of "Hungry Hungry Hippos" (aka "H3"). This language modeling architecture performs comparably to transformers, while admitting much longer context length: n log(n) rather than n^2 context scaling, for those technically inclined. Listen to learn about the major ideas and history behind H3, state space models, what makes them special, what products can be built with long-context language models, and hints of Dan and Tri's future (unpublished) research.To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.

Deep Papers is a podcast series featuring deep dives on today’s seminal AI papers and research. Hosted by AI Pub creator Brian Burns and Arize AI founders Jason Lopatecki and Aparna Dhinakaran, each episode profiles the people and techniques behind cutting-edge breakthroughs in machine learning. In this first episode, we’re joined by Long Ouyang and Ryan Lowe, research scientists at OpenAI and creators of InstructGPT. InstructGPT was one of the first major applications of Reinforcement Learning with Human Feedback to train large language models, and is the precursor to the now-famous ChatGPT. Listen to learn about the major ideas behind InstructGPT and the future of aligning language models to human intention.Read OpenAI's InstructGPT paper here: https://openai.com/blog/instruction-following/To learn more about ML observability, join the Arize AI Slack community or get the latest on our LinkedIn and Twitter.