Roy Schwartz

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models ACL 2026 How Quantization Shapes Bias in Large Language Models EACL 2026 Context Length Alone Hurts LLM Performance Despite Perfect Retrieval EMNLP 2025 From Tokens to Words: On the Inner Lexicon of LLMs ICLR 2025 On Pruning State-Space LLMs EMNLP 2025 Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers EMNLP 2024 Beyond Performance: Quantifying and Mitigating Label Bias in LLMs NAACL 2024 Transformers are Multi-State RNNs EMNLP 2024 Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images ICCV 2023 Curating Datasets for Better Performance with Example Training Dynamics ACL 2023 Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases ACL 2023 Finding the SWEET Spot: Analysis and Improvement of Adaptive Inference in Low Resource Settings ACL 2023 Textually Pretrained Speech Language Models NeurIPS 2023 VASR: Visual Analogies of Situation Recognition AAAI 2023 ABC: Attention with Bounded-memory Control ACL 2022 Data Contamination: From Memorization to Exploitation ACL 2022 Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias NAACL 2022 How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers EMNLP 2022 On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations NAACL 2022 WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models NeurIPS 2022 Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA NAACL 2021 Data Efficient Masked Language Modeling for Vision and Language EMNLP 2021 Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent EMNLP 2021 Expected Validation Performance and Estimation of a Random Variable’s Maximum EMNLP 2021 Extracting a Knowledge Base of Mechanisms from COVID-19 Papers NAACL 2021 Random Feature Attention ICLR 2021 A Formal Hierarchy of RNN Architectures ACL 2020 A Mixture of h - 1 Heads is Better than h Heads ACL 2020 Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics EMNLP 2020 The Right Tool for the Job: Matching Model and Instance Complexities ACL 2020 Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets NAACL 2019 Knowledge Enhanced Contextual Word Representations EMNLP 2019 PaLM: A Hybrid Parser and Language Model EMNLP 2019 RNN Architecture Learning with Sparse Regularization EMNLP 2019 Show Your Work: Improved Reporting of Experimental Results EMNLP 2019 A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications NAACL 2018 Annotation Artifacts in Natural Language Inference Data NAACL 2018 Bridging CNNs, RNNs, and Weighted Finite-State Machines ACL 2018 LSTMs Exploit Linguistic Attributes of Data ACL 2018 Rational Recurrences EMNLP 2018 SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference EMNLP 2018 Automatic Selection of Context Configurations for Improved Class-Specific Word Representations CoNLL 2017 The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task CoNLL 2017 Symmetric Patterns and Coordinations: Fast and Enhanced Representations of Verbs and Adjectives NAACL 2016 How Well Do Distributional Models Capture Different Types of Semantic Knowledge? ACL 2015 Symmetric Pattern Based Word Embeddings for Improved Word Similarity Prediction CoNLL 2015 Minimally Supervised Classification to Semantic Categories using Automatically Acquired Symmetric Patterns COLING 2014 Authorship Attribution of Micro-Messages EMNLP 2013 Learnability-Based Syntactic Annotation Design COLING 2012 Unsupervised SVMs: On the Complexity of the Furthest Hyperplane Problem COLT 2012 Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation ACL 2011