Opening AI's Black Box with Prof. David Bau, Koyena Pal, and Eric Todd of Northeastern University
In this episode, we dive deep into the inner workings of large language models with Professor David Bau and grad students Koyena Pal and Eric Todd from Northeastern University. Koyena shares insights from her Future Lens paper, which shows that even mid-sized language models think multiple tokens ahead. Eric discusses the fascinating concept of Function Vectors - complex patterns of activity spread across transformer layers that enable in-context learning. Professor Bau connects the dots between these projects and the lab's broader interpretability research agenda, identifying key abstractions that link low-level computations to higher-level model behaviors.
SPONSORS:
Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitive
ODF is where top founders get their start. Apply to join the next cohort and go from idea to conviction-fast. ODF has helped over 1000 companies like Traba, Levels and Finch get their start. Is it your turn? Go to http://beondeck.com/revolution to learn more.
Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off www.omneky.com
The Brave search API can be used to assemble a data set to train your AI models and help with retrieval augmentation at the time of inference. All while remaining affordable with developer first pricing, integrating the Brave search API into your workflow translates to more ethical data sourcing and more human representative data sets. Try the Brave search API for free for up to 2000 queries per month at https://bit.ly/BraveTCR
Plumb is a no-code AI app builder designed for product teams who care about quality and speed. What is taking you weeks to hand-code today can be done confidently in hours. Check out https://bit.ly/PlumbTCR for early access.
Head to Squad to access global engineering without the headache and at a fraction of the cost: head to choosesquad.com and mention “Turpentine” to skip the waitlist.
TIMESTAMPS:
(00:00) Intro
(04:03) Reverse Engineering AI
(10:10) Factual Knowledge Localization
(16:34) Sponsors: Oracle | Omneky | On Deck
(18:27) Future Lens Paper Intro
(23:54) Choosing GPT-J
(26:54) Vocabulary Prediction
(30:36) Sponsors: Brave | Plumb | Squad
(33:13) Fixed Prompt
(35:57) Soft Prompt
(41:32) Future Lens Results Analysis
(51:50) Tooling & Open Source Code
(56:07) Larger Models & Mamba Probes
(1:04:10) Function Vectors Paper
(1:09:39) Extracting & Patching Vectors
(1:13:30) Encoding Task Understanding
(1:15:36) Expert Models Implications
(1:18:09) Conclusion
Are LLMs Good at Causal Reasoning? with Robert Osazuwa Ness - #638
Today we’re joined by Robert Osazuwa Ness, a senior researcher at Microsoft Research, Professor at Northeastern University, and Founder of Altdeep.ai. In our conversation with Robert, we explore whether large language models, specifically GPT-3, 3.5, and 4, are good at causal reasoning. We discuss the benchmarks used to evaluate these models and the limitations they have in answering specific causal reasoning questions, while Robert highlights the need for access to weights, training data, and architecture to correctly answer these questions. The episode discusses the challenge of generalization in causal relationships and the importance of incorporating inductive biases, explores the model's ability to generalize beyond the provided benchmarks, and the importance of considering causal factors in decision-making processes.
The complete show notes for this episode can be found at twimlai.com/go/638.
AI Trends 2023: Causality and the Impact on Large Language Models with Robert Osazuwa Ness - #616
Today we’re joined by Robert Osazuwa Ness, a senior researcher at Microsoft Research, to break down the latest trends in the world of causal modeling. In our conversation with Robert, we explore advances in areas like causal discovery, causal representation learning, and causal judgements. We also discuss the impact causality could have on large language models, especially in some of the recent use cases we’ve seen like Bing Search and ChatGPT. Finally, we discuss the benchmarks for causal modeling, the top causality use cases, and the most exciting opportunities in the field.
The complete show notes for this episode can be found at twimlai.com/go/616.
Hypergraphs, Simplicial Complexes and Graph Representations of Complex Systems with Tina Eliassi-Rad - #547
Today we continue our NeurIPS coverage joined by Tina Eliassi-Rad, a professor at Northeastern University, and an invited speaker at the I Still Can't Believe It's Not Better! Workshop. In our conversation with Tina, we explore her research at the intersection of network science, complex networks, and machine learning, how graphs are used in her work and how it differs from typical graph machine learning use cases. We also discuss her talk from the workshop, “The Why, How, and When of Representations for Complex Systems”, in which Tina argues that one of the reasons practitioners have struggled to model complex systems is because of the lack of connection to the data sourcing and generation process. This is definitely a NERD ALERT approved interview!
The complete show notes for this episode can be found at twimlai.com/go/547
NLP for Mapping Physics Research with Matteo Chinazzi - #353
Predicting the future of science, particularly physics, is the task that Matteo Chinazzi, an associate research scientist at Northeastern University focused on in his paper Mapping the Physics Research Space: a Machine Learning Approach. In addition to predicting the trajectory of physics research, Matteo is also active in the computational epidemiology field. His work in that area involves building simulators that can model the spread of diseases like Zika or the seasonal flu at a global scale.
Causality 101 with Robert Osazuwa Ness - #342
Today Robert Osazuwa Ness, ML Research Engineer at Gamalon and Instructor at Northeastern University joins us to discuss Causality, what it means, and how that meaning changes across domains and users, and our upcoming study group based around his new course sequence, “Causal Modeling in Machine Learning," for which you can find details at twimlai.com/community.