Update 2024-1-16-seminar.md

_posts/2024-1-16-seminar.md

@@ -25,7 +25,7 @@ tags:
 Discover the realm of Large Language Models (LLMs) and their burgeoning applications, a domain that has garnered substantial attention, particularly in the wake of ChatGPT's release in November 2022. This course serves as a structured introduction to cutting-edge methodologies and tools aimed at bolstering the **trustworthiness of LLMs**, spanning both their theoretical underpinnings and practical implementations. Organized into three meticulously designed modules, Module I provides a deep dive into the foundational LLMOps stack, coupled with hands-on experience in constructing LLM applications using LlamaIndex, culminating in a rigorous evaluation of a Retrieval-Augmented Generation question-answering application. Module II unveils the pivotal roles LLMs play in critical domains such as healthcare, education, and security, fostering innovative project ideas through collaborative brainstorming sessions. In Module III, students delve into advanced LLM (app) evaluation methodologies, encompassing diverse topics including relevance, groundedness, confidence, calibration, uncertainty, explainability, privacy, fairness, toxicity, and adversarial attacks. Armed with these refined analytical skills, students embark on an immersive quarter-long course project, making this course a comprehensive and academically rigorous exploration of the LLM landscape.
 
 ## Prerequisites
-Students should have experience with machine learning, data analytics, and deep learning. Strong programming skills in a high-level language such as Python, as well as frameworks for rapid ML prototyping, e.g., PyTorch, Tensorflow, Keras, etc. are essential for implementing and experimenting with the concepts covered in this course. While not mandatory, familiarity with natural language processing would be advantageous.
+Students should have experience with machine learning, data analytics, and deep learning. Strong programming skills in a high-level language such as Python, as well as frameworks for rapid deep learning prototyping, e.g., PyTorch, Tensorflow, Keras, etc., are essential for implementing and experimenting with the concepts covered in this course. While not mandatory, familiarity with natural language processing would be advantageous.
 
 ## Course Format
 The course is a [role-playing paper reading seminar](https://colinraffel.com/blog/role-playing-seminar.html) that is structured around reading, presenting, and discussing weekly papers. Each class will involve the presentation and discussion of two papers. Each student will have a unique, rotating role per week. This role defines the lens through which each student reads the paper and determines what they prepare for the group in-class discussion. All students, irrespective of their role, are expected to have read the paper readings of each corresponding session before class and come to class ready to discuss. There will be no exams or traditional assignments. Instead, throughout the course, students will engage in practical hands-on projects and discussions to identify and work on open research questions on a variety of topics in trustworthy LLMs.