Ellie Pavlick

A Knapsack by Any Other Name: Presentation impacts LLM performance on NP-hard problems EMNLP 2025 Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline EMNLP 2025 What is an “Abstract Reasoner”? Revisiting Experiments and Arguments about Large Language Models CONLL 2025 Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting ICLR 2025 The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling ICLR 2025 What is an “Abstract Reasoner”? Revisiting Experiments and Arguments about Large Language Models ACL 2025 Does Training on Synthetic Data Make Models Less Robust? NAACL 2025 Re-Evaluating Evaluation for Multilingual Summarization EMNLP 2024 Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects NIPS 2024 Language Models Implement Simple Word2Vec-style Vector Arithmetic NAACL 2024 Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models NIPS 2024 mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? NAACL 2024 Does CLIP Bind Concepts? Probing Compositionality in Large Image Models EACL 2024 Circuit Component Reuse Across Tasks in Transformer Language Models ICLR 2024 Can Neural Networks Learn Implicit Logic from Physical Reasoning? ICLR 2023 Emergence of Abstract State Representations in Embodied Sequence Modeling EMNLP 2023 Characterizing Mechanisms for Factual Recall in Language Models EMNLP 2023 Analyzing Modular Approaches for Visual Question Decomposition EMNLP 2023 Are Language Models Worse than Humans at Following Prompts? It’s Complicated EMNLP 2023 Linearly Mapping from Image to Text Space ICLR 2023 Break It Down: Evidence for Structural Compositionality in Neural Networks NIPS 2023 Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex NIPS 2022 Mapping Language Models to Grounded Conceptual Spaces ICLR 2022 The MultiBERTs: BERT Reproductions for Robustness Analysis ICLR 2022 Do Prompt-Based Models Really Understand the Meaning of Their Prompts? NAACL 2022 Do Trajectories Encode Verb Meaning? NAACL 2022 Pretraining on Interactions for Learning Grounded Affordance Representations NAACL 2022 AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ACL 2021 Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering ACL 2021 Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions ACL 2021 Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color CONLL 2021 Frequency Effects on Syntactic Rule Learning in Transformers EMNLP 2021 “Was it “stated” or was it “claimed”?: How linguistic bias affects generative language models EMNLP 2021 Does Vision-and-Language Pretraining Improve Lexical Grounding? EMNLP 2021 Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color EMNLP 2021 Predicting Inductive Biases of Pre-Trained Models ICLR 2021 Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering IJCNLP 2021 AND does not mean OR: Using Formal Languages to Study Language Models’ Representations IJCNLP 2021 Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions IJCNLP 2021 Grounding Language to Non-Markovian Tasks with No Supervision of Task Specifications RSS 2020 What Happens To BERT Embeddings During Fine-tuning? EMNLP 2020 A Visuospatial Dataset for Naturalistic Verb Learning COLING 2020 Are “Undocumented Workers” the Same as “Illegal Aliens”? Disentangling Denotation and Connotation in Vector Spaces EMNLP 2020 Interpretability and Analysis in Neural NLP ACL 2020 Robot Object Retrieval with Contextual Natural Language Queries RSS 2020 Using Grounded Word Representations to Study Theories of Lexical Concepts NAACL 2019 Planning with State Abstractions for Non-Markovian Task Specifications RSS 2019 BERT Rediscovers the Classical NLP Pipeline ACL 2019 How well do NLI models capture verb veridicality? IJCNLP 2019 How well do NLI models capture verb veridicality? EMNLP 2019 Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling ACL 2019 Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference ACL 2019 What do you learn from context? Probing for sentence structure in contextualized word representations ICLR 2019 WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse EMNLP 2018 Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation EMNLP 2018 Learning Scalar Adjective Intensity from Paraphrases EMNLP 2018 Identifying 1950s American Jazz Musicians: Fine-Grained IsA Extraction via Modifier Composition ACL 2017 The Gun Violence Database: A new task and data set for NLP EMNLP 2016 Simple PPDB: A Paraphrase Database for Simplification ACL 2016 Most “babies” are “little” and most “problems” are “huge”: Compositional Entailment in Adjective-Nouns ACL 2016 Tense Manages to Predict Implicative Behavior in Verbs EMNLP 2016 Crowdsourcing for NLP NAACL 2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop ACL 2015 PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification ACL 2015 FrameNet+: Fast Paraphrastic Tripling of FrameNet ACL 2015 Domain-Specific Paraphrase Extraction ACL 2015 Adding Semantics to Data-Driven Paraphrasing ACL 2015 FrameNet+: Fast Paraphrastic Tripling of FrameNet IJCNLP 2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop IJCNLP 2015 Domain-Specific Paraphrase Extraction IJCNLP 2015 Adding Semantics to Data-Driven Paraphrasing IJCNLP 2015 Inducing Lexical Style Properties for Paraphrase and Genre Differentiation NAACL 2015 PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification IJCNLP 2015 Are Two Heads Better than One? Crowdsourced Translation via a Two-Step Collaboration of Non-Professional Translators and Editors ACL 2014