Program

Keynote Speaker (remote): Prof. Yulia Tsvetkov, University of Washington

"Language Models under the Microscope:  Can We Track Invisible Biases and Should We Sanitize the Models?"

Yulia Tsvetkov is an associate professor at the Paul G. Allen School of Computer Science & Engineering at University of Washington. Her research group works on fundamental advancements to large language models, multilingual NLP, and AI ethics. This research is motivated by a unified goal: to extend the capabilities of human language technology beyond individual populations and across language boundaries, thereby making NLP tools available to all users. Prior to joining UW, Yulia was an assistant professor at Carnegie Mellon University, a postdoc at Stanford, and a PhD student at CMU. Prior to that, she was fortunate to complete her Master's with Shuly Wintner who introduced her to NLP, and has been an inspiring mentor, collaborator, and friend since then. Yulia is a recipient of NSF CAREER, Sloan Fellowship, Okawa Research award, and several paper awards and runner-ups at NLP, ML, and CSS conferences.

Session 1: Cognitive Modeling, CSS, Analysis (session chair: Rotem Dror)

• Fine-Grained Prediction of Reading Comprehension from Eye Movements
  (Omer Shubi, Yoav Meiri, Cfir Avraham Hadar, Yevgeni Berzak)

• A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns
  (Asaf Yehudai, Taelin Karidi, Gabriel Stanovsky, Ariel Goldstein, Omri Abend)

• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
  (Victoria Basmov, Yoav Goldberg, Reut Tsarfaty)

• Unveiling Polarization Trends in the Knesset Proceedings
  (Gili Goldin, Ella Rabinovich, Shuly Wintner)

Session 2: Evaluation & Benchmarking, Analysis (session chair: Reut Tsarfaty)

• Motivational Interviewing Transcripts Annotated with Global Scores
  (Ben Cohen, Moreah Zisquit, Stav Yosef, Doron Friedman, Kfir Bar)

• Estimating Knowledge in Large Language Models Without Generating a Single Token
  (Daniela Gottesman, Mor Geva)

• Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers
  (Amit Ben Artzy, Roy Schwartz)

• Bencmark Agreement Testing Done Right: A Guide for LLM Benchmark Evaluation
  (Yotam Perlitz, Ariel Gera, Ofir Arviv, Asaf Yehudai, Elron Bandel, Eyal Shnarch, Michal Shmueli-Scheuer, Leshem Choshen)

• Probing Morphological Transformers for Phonological Features
  (Gal Astrach, Yuval Pinter)

Special Oral Session

Panel: On the Roles of Academia and Industry in the Modern NLP Research

Liat Ein-Dor (IBM)
Shalom Lappin (Queen Mary University of London)
Gabriel Stanovsky (HUJI)
Kfir Bar (Reichman University)
Hadas Orgad (Technion)

moderator: Yuval Pinter (Ben Gurion University of the Negev and Amazon Research)

Session 3: Multimodality, Analysis (session chair: Oren Tsur)

• Explicating the Implicit: Argument Detection Beyond Sentence Boundaries
  (Paul Roit, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, Ido Dagan)

• AggregHate: An Efficient Aggregative Approach for the Detection of Hatemongers on Social Platforms
  (Tom Marzea, Oren Tsur)

• On the Semantic Latent Space of Diffusion-Based Text-To-Speech Models
  (Miri Varshavsky-Hassid, Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, Ehud Rivlin)

• Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
  (Mor Ventura, Roi Reichart, Eyal Ben-David, Anna Korhonen)

Closing remarks