CS 224V

Conversational Virtual Assistants with Deep Learning

Fall 2023

Final Project Expo

CS 224V is hosting the final project expo on Wednesday, December 6th, 3:00pm - 5:30pm, with student presentations from 3:00pm - 4:20pm in Gates B3 and a poster session from 4:20pm - 5:30pm.

50 student teams in CS 224V worked to create LLM-powered conversational assistants across a wide range of applications from medicine, mental health, law, finance, education, government, journalism, security, fitness, fashion, and games, with different modalities (speech, GUI, video) and across different cultures. Where appropriate, LLMs are grounded to eliminate hallucination using information and database retrieval. Come learn about the challenges they tackled and their solutions as they present their posters at the Project Expo! This is a great chance to meet top students in conversational assistant technology.

About CS 224V

Generative AI, and in particular Large Language Models (LLMs) such as GPT-4, has already changed how we work and study. But this is just the beginning, as it has the potential of assisting and perhaps eventually automating knowledge workers in all areas, from law, medicine, to teaching and mental health therapists. This course will focus on the general principles and the latest research on methodologies and tools that can be applied to all domains. This is a project-oriented course, where students will gain hands-on experience in either methodology research or applying the concepts to create useful assistants for a domain of their choice.

Topics include:

  • Growing LLMs' knowledge through a combination of manual supervised learning and self-learning.

  • Stopping LLMs from hallucination by grounding them with external corpora of knowledge, which is necessary for handling new, live, private as well as long-tail data.

  • Handling external data corpora in different domains including structured and unstructured data.

  • Experimentation and evaluation of conversational assistants based on LLMs.

  • Controlling LLMs to achieve tasks.

  • Persuasive LLMs.

  • Multilingual assistants.

  • Combining voice and graphical interfaces.


There will be two homeworks at the beginning of the quarter, where students will create hallucination-free LLM-based agents using given tools. Students can build upon this work for their project in the rest of the quarter. Homework will be done in groups of 2.

👩‍🏫 Instructor Monica Lam
(lam at cs)
🧑‍🏫 Head TA Shicheng Liu
(shicheng at cs)
🧑‍🏫 TA Tommy Bruzzese
🧑‍🏫 TA Arvind Sridhar
🧑‍🏫 TA Amol Singh
🕒 Time Mon, Wed 3:00-4:20pm
🏫 Location Gates Room B3
💳 Credits 3-4 units

Office Hours

Shicheng Liu Fri 11:00 am - 12:00 pm, Gates 498,
Zoom meeting link


Lectures: Monday/Wednesday 3:00-4:20pm in person in Gates B3. Attendance is mandatory.

Recordings: video recordings of the lecture can be found on Canvas.

Slides: can be found on the Schedule and in the lecture slides folder on Canvas. Posted lecture slides are missing important details to facilitate student participation. Please make sure you watch the lectures.

Homework: can be found on the Schedule and submissions will be on Gradescope.

Contact: Students should ask all course-related questions on Ed, where you will also find announcements. For external inquiries, personal matters, or in emergencies, you can send an email to our staff email cs224v-aut2324-staff@lists.stanford.edu

Academic accommodations: If you need an academic accommodation based on a disability, you should initiate the request with the Office of Accessible Education (OAE). The OAE will evaluate the request, recommend accommodations, and prepare a letter for the teaching staff. Once you receive the letter, send it to the course staff email at cs224v-aut2324-staff@lists.stanford.edu. Students should contact the OAE as soon as possible since timely notice is needed to coordinate accommodations.

Audit Requests: To audit the course, please send an email to course staff email at cs224v-aut2324-staff@lists.stanford.edu, with the subject line "audit cs224v request."

Course Participation: We offer the course on SCPD to serve remote students; it is not to allow students take conflicting courses. In-class attendance and participation are an important part of the course. We allocate 15% of the course grade to class participation, which is important to make the most out of the course.

  1. If you are a local student, 5% of the course grade is allocated to in-class attendance and participation.
  2. We allocate 10% and 15% of the grade to local and remote students, respectively, to (1) your weekend updates, and (2) interaction with your project mentor every week.
  3. Contributions in helping others on Ed will be awarded with bonus points.


The class is currently full. We are accepting enrollment requests via waitlist. To join the waitlist, please (1) join the waitlist on Axess, and (2) fill out this form. Permission numbers will be distributed on a rolling basis as spaces open.

Prerequisites: one of LINGUIST 180/280, CS 124, CS 224N, CS 224S, 224U.

Update (9/22): CS224V has limited enrollment so as to provide adequate project/research supervision to students. At this point, we have given out the remaining spots to a few more students who need to take this course or have demonstrated that they need little project supervision. We anticipate that only a few spots may open up due to attrition; if you have not heard from us, it is unlikely that we can accommodate you. We apologize that we cannot accommodate all the students wishing to take the course this year.


Grading is according to the following scheme: