NENLP 2023 Meetup Schedule

10:00-10:15	Breakfast
10:15-10:30	Welcome remarks (Anna Rumshisky)
10:30-11:50	Spotlight talks (session chair: Namrata Shivagunde) 10:30-10:50 Afra Feyza Akyurek Boston university RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs 10:50-11:10 Zhaofeng Wu MIT Transparency Helps Reveal When Language Models Learn Meaning 11:10-11:30 Vlad Lialin UMass Lowell Parameter-efficient fine-tuning. A survey 11:30-11:50 Denis Jered McInerney Northeastern University CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models
11:50-12:35	Keynote 1: Shiv Vitaladevuni (Amazon Alexa AI)
12:35-1:30	Lunch
1:30-3:00	Poster session
3:00-4:00	Spotlight talks (session chair: Vijeta Deshpande) 3:00-3:20 Jack Merullo Brown University Feed Forward Networks Implement Abstract Functions that Transfer Across Contexts 3:20-3:40 Varshini Subhash, Anna Bialas Harvard University Why do universal adversarial attacks work on large language models? 3:40-4:00 Erica Cai, Brendan O'Connor UMass Amherst Efficient and modality-independent zero-shot event extraction of entities with actor representatives
4:00-4:45	Keynote 2: Matthew McDermott (Harvard University) (session chair: Vladislav Lialin)
4:45-5:00	Closing remarks

Poster session

Sheridan Feucht	Brown University	Can Visual Models Learn an Abstract Relation from Data?
Catherine Chen	Brown University	Evaluating Search Explainability with Psychometrics and Crowdsourcing
Alex Gu	MIT	ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications
Michal Golovanevsky	Brown University	Scalable and Interpretable Multimodal Attention
Zhaofeng Wu	MIT	Transparency Helps Reveal When Language Models Learn Meaning
Isidora Tourni	Boston University	An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model’s behavior and sentences’ contribution
William Rudman	Brown University	Stable Anisotropic Regularization
Aaron Traylor	Brown University	Analyzing Transformer Mechanisms for Cognitive Branching
Qinan Yu, Alyssa Loo	Brown University	Are Language Models Worse than Humans at Following Prompts? It's Complicated
Ankita Gupta	UMass Amherst	ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
Chau Pham and Marisa Hudspeth	UMass Amherst	Gender and Power in Latin Narratives
Charles Lovering	Brown University	Training Priors Predict Text-To-Image Model Performance
Afra Feyza Akyurek	Boston university	RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Evan Hernandez	MIT	Latent Linear Relational Embeddings in Transformer Language Models
Vlad Lialin	UMass Lowell	Parameter-efficient fine-tuning. A survey
Denis Jered McInerney	Northeastern University	CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models
Jack Merullo	Brown University	Feed Forward Networks Implement Abstract Functions that Transfer Across Contexts
Varshini Subhash, Anna Bialas	Harvard University	Why do universal adversarial attacks work on large language models?
Erica Cai, Brendan O'Connor	UMass Amherst	Efficient and modality-independent zero-shot event extraction of entities with actor representatives