Hadas Orgad

11 papers · 2022–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+4 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 👥 Mega-Team · Squad

🤝 Dynamic Duo (11) 🗃️ Keyword Collector (53) 📈 Trend Setter 💎 Century Club · Bronze

Venues

NAACL (4) ACL (3) ICCV (1) ICLR (1) ICML (1) WACV (1)

Top co-authors

Yonatan Belinkov (11) David Bau (3) Dana Arad (3) Michael Toker (3) Aaron Mueller (2) Tal Haklay (2) Jaden Fried Fiotto-Kaufman (1) Adam Belfki (1) Zorik Gekhman (1) Aruna Sankaranarayanan (1)

Research topics

Deep Learning (8) Artificial Intelligence (6) Machine Learning (6) Core AI (6) Application Areas (5) Models (5) Computer Vision (4) Generation (4) Core Methods (3) Natural Language Processing (1) Applications (1) Learning Types (1) Optimization & Theory (1) Resources & Methods (1) Techniques (1)

Keywords

diffusion model (4) model editing (3) text encoder (2) text-to-image diffusion (2) mechanistic interpretability (2) text-to-image model (1) text-to-image generation (1) image generation (1) latent representation (1) hallucination detection (1) bias mitigation (1) language model (1) content moderation (1) closed-form solution (1) sparse autoencoder (1) error detection (1) pre-trained language model (1) parameter efficiency (1) sentiment classification (1) algorithmic fairness (1)

Papers

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations ICLR 2025 MIB: A Mechanistic Interpretability Benchmark ICML 2025 Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models NAACL 2025 Position-aware Automatic Circuit Discovery ACL 2025 Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines ACL 2024 ReFACT: Updating Text-to-Image Models by Editing the Text Encoder NAACL 2024 Unified Concept Editing in Diffusion Models WACV 2024 BLIND: Bias Removal With No Demographics ACL 2023 Editing Implicit Assumptions in Text-to-Image Diffusion Models ICCV 2023 Choose Your Lenses: Flaws in Gender Bias Evaluation NAACL 2022 How Gender Debiasing Affects Internal Model Representations, and Why It Matters NAACL 2022