Events

Our reading group has a new home!

👉 We’ve moved all info and updates about our events and reading group to GitHub Discussions.

---

On this page, we post information about upcoming events within the NLP@DSAI group.

Reading Group

We hold a Natural Language Processing reading group roughly every 3 weeks.

For each meeting, a paper is selected that all members agree to read. A designated member (the curator) prepares a concise summary of the paper and a set of notes which they share with the group. Before the meeting, all members are expected to read the paper and write their thoughts and concerns in the shared notes. Then, during the meeting the curator guides the group through the structured discussion based on the questions and themes emerging from the shared notes. We are committed to maintaining a respectful and positive atmosphere, where members are encouraged to critique ideas constructively and listen actively to each other.

If you would like to join the reading group, please send an email to our coordinator.

Upcoming meetings

• TBD - DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Previous meetings

• 2025-02-27, 10:00–12:00, - Algebraic Positional Encodings, with invited guest Jean-Philippe Bernardy
• 2024-12-06, 15:00–17:00, EDIT-5128 - Visual Instruction Tuning
• 2024-11-15, 13:00–15:00, EDIT-6128 - RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
• 2024-10-17, 13:00–15:00, EDIT-5128 - Analyzing Semantic Change through Lexical Replacements and Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types, with invited guests Pierluigi Cassotti and Nina Tahmasebi
• 2024-09-25, 13:00–15:00, EDIT-5128 - Using Large Language Model Annotations for the Social Sciences: A General Framework of Using Predicted Variables in Downstream Analyses
• 2024-09-05 - Critical questions for Big Data
• 2024-05-30 - Out of One, Many: Using Language Models to Simulate Human Samples
• 2024-04 - LOCOST: State-Space Models for Long Document Abstractive Summarization
• 2024-03-28 - Naturalistic Causal Probing for Morpho-Syntax
• 2024-03-07 - Understanding Transformer Memorization Recall Through Idioms
• 2023-12-21 - Detecting Pretraining Data from Large Language Models
• 2023-11-21 - Testing Causal Theories with Learned Proxies
• 2023-10-26 - Two papers on the application of causal mediation analysis in NLP model analysis
  • Investigating Gender Bias in Language Models Using Causal Mediation Analysis
  • Locating and Editing Factual Associations in GPT
• 2023-10-10 - Causal Abstractions of Neural Networks
• 2023-09-20 - Language Models (Mostly) Know What They Know
• 2023-09-05 - When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories