Invited Talks

2026

Barely Legal: AI Introduction for Law Students

PDF
  • Jan 2026 Social Media, AI, and Democracy class, Law Dept, Bar-Ilan University ๐Ÿ‡ฎ๐Ÿ‡ฑ
2025

Memorizing Distributions: Generative Models Recall More Than Verbatim Instances

PDF
  • Aug 2025 The First Workshop on LLM Memorization @ACL 2025, Vienna, Austria ๐Ÿ‡ฆ๐Ÿ‡น

On "Emergent Abilities" and Simple Training Data Statistics

  • Apr 2025 RIKEN Tokyo, Japan ๐Ÿ‡ฏ๐Ÿ‡ต
2024

The Simpson and Bias Amplification Paradoxes

PDF
  • Mar 2024 Dagstuhl Seminar, Germany ๐Ÿ‡ฉ๐Ÿ‡ช

What's In My Big Data and Its Implications on Models

PDF
  • May 2024 IBM Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • May 2024 Bar-Ilan University, Ramat-Gan, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • May 2024 Technion, Haifa, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Mar 2024 University of Edinburgh, Edinburgh, Scotland ๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟ
  • Mar 2024 Ludwig Maximilian University of Munich (LMU), Munich, Germany ๐Ÿ‡ฉ๐Ÿ‡ช
  • Feb 2024 University of Southern California (USC), Los Angeles, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Feb 2024 University of California Santa Barbara (UCSB), USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Feb 2024 University of California Los Angeles (UCLA), USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Nov 2023 ร‰cole Polytechnique Fรฉdรฉrale de Lausanne (EPFL), Switzerland ๐Ÿ‡จ๐Ÿ‡ญ
2023

My Intended Dissertation, It's (Retrospective) Disruption, And My Current Research

PDF
  • Apr 2023 Georgetown University, DC, USA ๐Ÿ‡บ๐Ÿ‡ธ
2022

Measuring Causal Effects of Data Statistics on Language Model Predictions

PDF
  • Jun 2022 University of Cambridge, UK ๐Ÿ‡ฌ๐Ÿ‡ง
  • May 2022 University of Copenhagen, Denmark ๐Ÿ‡ฉ๐Ÿ‡ฐ

Causal Attributions in Language Models

PDF
  • Feb 2022 ETH Zรผrich, Switzerland ๐Ÿ‡จ๐Ÿ‡ญ
  • Dec 2021 The Hebrew University of Jerusalem, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Dec 2021 New York University (NYU), USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Nov 2021 The University of British Columbia (UBC), Vancouver, Canada ๐Ÿ‡จ๐Ÿ‡ฆ
  • Nov 2021 AI2, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Nov 2021 University of California Irvine (UCI), USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Nov 2021 UT Austin, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Jun 2021 University of California Berkeley, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Apr 2021 Carnegie Mellon University (CMU), USA ๐Ÿ‡บ๐Ÿ‡ธ
2021

Complex Commonsense Reasoning & Why We Are Not There Yet

PDF

Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

PDF
  • Jun 2021 IDC Herzliya, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Feb 2021 Google, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Jan 2021 reciTAL, Paris, France ๐Ÿ‡ซ๐Ÿ‡ท

Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema

PDF
  • Oct 2021 ISCOL, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Dec 2020 AI2, Seattle, USA ๐Ÿ‡บ๐Ÿ‡ธ
  • Dec 2020 Microsoft, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
2020

Unsupervised Distillation Of Syntactic Information From Contextualized Word Representations

PDF
  • Nov 2020 Carnegie Mellon University (CMU), USA ๐Ÿ‡บ๐Ÿ‡ธ

How Large are Lions? Inducing Distributions over Quantitative Attributes

PDF
  • Jan 2020 DataHack, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
2019

Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution

PDF
  • Nov 2019 IBM Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • May 2019 Citi Innovation lab, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Apr 2019 Inria Lab, Paris, France ๐Ÿ‡ซ๐Ÿ‡ท

How Large are Lions? Inducing Distributions over Quantitative Attributes

PDF
  • Sep 2019 ISCOL, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Mar 2019 Excellence student talk, Bar Ilan University, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Feb 2019 University of Pennsylvania, Philadelphia, USA ๐Ÿ‡บ๐Ÿ‡ธ

Adversarial Removal of Demographic Attributes in Machine Learning Systems

PDF
  • Feb 2019 TextKernel, Amsterdam, Netherlands ๐Ÿ‡ณ๐Ÿ‡ฑ
2018

Adversarial Removal of Demographic Attributes from Text Data

PDF
  • Nov 2018 The University Of Sheffield, UK ๐Ÿ‡ฌ๐Ÿ‡ง
  • Nov 2018 Imperial College London, UK ๐Ÿ‡ฌ๐Ÿ‡ง
  • Oct 2018 PayPal, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Oct 2018 News, Economics and AI Meetup, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Oct 2018 Intuit, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ
  • Oct 2018 Microsoft Research, Israel ๐Ÿ‡ฎ๐Ÿ‡ฑ