I hereby solicit suggestions for the video of the day. Please email me your ideas with explanations. Selected entries will win 5 homework points. If your video is played at the beginning of class, you must also briefly explain something about the video and something about yourself - in person.
https://pollev.com/slade You may also download the app to your phone. Use the "slade" poll id.
Here is a practice exam. (solutions to practice exam) Ignore problems 3, 4, 5(a), and 5(e). TC-201 is not in scope for this exam. However, tail recursion is.
There will be a UNIX question, as in the first midterm. sample UNIX transcript (solutions)
Review session: TBA.
As before, I recommend using Yale's Clarity and Google experimental tutor as sources for review questions.
Title: Prompting is *not* all you need! Or why Multi-LLM Collaboration MattersAbstract:
Recent years have witnessed the rise of increasingly larger and more sophisticated language models (LMs) capable of performing every task imaginable, sometimes at (super)human level. In this talk, I will argue that in many realistic scenarios solely relying on a single general-purpose LLM is suboptimal. A single LLM is likely to under-represent real-world data distributions, heterogeneous skills, and task-specific requirements. Instead, I will discuss Multi-LLM collaboration as an alternative for compositional generative modeling. This approach leads to more effective problem-solving while being more inclusive and explainable. I will focus on two case studies, video summarization for movies (long input) and narrative story generation (long output). I will demonstrate how these tasks can be tackled by orchestrating a society of agents — each pursing individual goals while collectively working toward the overall task objective. Additionally, I will explore how these agent societies leverage heterogeneous tools, collaborate, and share information to improve performance.
Bio:
Mirella Lapata is professor of natural language processing in the School of Informatics at the University of Edinburgh. Her research focuses on getting computers to understand, reason with, and generate natural language. She is the first recipient (2009) of the British Computer Society and Information Retrieval Specialist Group (BCS/IRSG) Karen Sparck Jones award and a Fellow of the Royal Society of Edinburgh, the ACL, and Academia Europaea.
Mirella has also received best paper awards in leading NLP conferences and has served on the editorial boards of the Journal of Artificial Intelligence Research, the Transactions of the ACL, and Computational Linguistics. She was president of SIGDAT (the group that organizes EMNLP) in 2018. She has been awarded an ERC consolidator grant, a Royal Society Wolfson Research Merit Award, and a UKRI Turing AI World-Leading Researcher Fellowship.
Website: https://homepages.inf.ed.ac.uk/mlap/
Title: Robust NLP: Can We Do Better Than Bigger?Abstract: The robust text understanding and generation capabilities of today’s NLP has been driven by the assumption that larger models and larger datasets improve predictive performance. However, this approach may not be sufficient to address real-world challenges, particularly in low-resource languages and domains.
In this talk, I will argue that robust NLP requires us to move beyond accuracy and perplexity as evaluation metrics. Towards this goal, I will present the idea of learning from knowledge rather than data, which exploits input and label meaning, in the presence of invariant domain knowledge. This approach generalizes traditional machine learning and has shown promise across multiple NLP problems. I will connect back to the theme of low-resource domains by presenting a text-based crisis counseling application. I will conclude by outlining future research directions around the theme of making inferences about text across domains despite limited data and compute resources.
Bio: Vivek Srikumar is an associate professor in the Kahlert School of Computing at the University of Utah. His research lies in the areas of artificial intelligence, natural language processing and machine learning, and has been primarily driven by questions arising from the need to efficiently reason about textual data with limited supervision. His research has been published at various AI, NLP and ML venues, and has been recognized by a paper award at EMNLP 2014, and honorable mentions from CoNLL 2019 and the IEEE Micro magazine. His work has been supported by research grants from NSF, US-Israel BSF, NIH, and awards from Google, Intel, Nvidia and Verisk. He has served as associate program chair of AAAI 2022 and the program co-chair of CoNLL 2022 and ACL 2024. Furthermore, he has organized several workshops hosted at the primary ML and NLP conferences around the theme of how learning and structured knowledge intersect. He was a post-doctoral scholar at Stanford University before moving to Utah, and prior to that, in 2013, he obtained his PhD from the University of Illinois at Urbana-Champaign.
Website: https://svivek.com
You are invited to create a music video for this song. Here are the rules:
In class on February 3rd, I introduced Toch's Geographical Fugue (wiki + score) as well as my derived Internet Fugue Here is a sample recording of the first 32 bars by a guest artist using GarageBand. It took 10 minutes and it shows.
You are invited to perform the Internet Fugue either on video, or (preferably) live in class. The rules and rewards are the same as above.
Gates.html (jupyter) computer memory - sequential circuits.
hw5 review.
racket hash tables We use mutable hashes in this assignment.
make-hash hash-ref hash-keys hash-set! hash-copy hash-has-key?