pith. sign in

Ellie Pavlick

Identifiers

  • name variant Ellie Pavlick 0.60 · backfill

Papers (70)

  1. Source-Modality Monitoring in Vision-Language Models cs.CL · 2026 · author #3
  2. Shared Lexical Task Representations Explain Behavioral Variability In LLMs cs.CL · 2026 · author #8
  3. Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling cs.LG · 2026 · author #2
  4. How Do Language Models Compose Functions? cs.CL · 2025 · author #2
  5. Whither symbols in the era of advanced neural networks? cs.AI · 2025 · author #4
  6. What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models cs.CL · 2025 · author #3
  7. Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility cs.CL · 2025 · author #6
  8. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities cs.CL · 2025 · author #814
  9. LLMs model how humans induce logically structured rules cs.AI · 2025 · author #2
  10. How Do Vision-Language Models Process Conflicting Information Across Modalities? cs.CL · 2025 · author #3
  11. Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline cs.CL · 2025 · author #4
  12. Does Training on Synthetic Data Make Models Less Robust? cs.CL · 2025 · author #2
  13. Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers cs.CL · 2024 · author #4
  14. The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling cs.CL · 2024 · author #5
  15. Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects cs.CV · 2024 · author #6
  16. Talking Heads: Understanding Inter-layer Communication in Transformer Language Models cs.CL · 2024 · author #3
  17. Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting cs.CL · 2024 · author #4
  18. Lessons from the Trenches on Reproducible Evaluation of Language Models cs.CL · 2024 · author #22
  19. mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? cs.CL · 2024 · author #3
  20. Bayesian Preference Elicitation with Language Models cs.CL · 2024 · author #3
  21. Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction cs.HC · 2024 · author #9
  22. The dynamic interplay between in-context and in-weight learning in humans and neural networks cs.NE · 2024 · author #2
  23. Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks cs.AI · 2024 · author #4
  24. Analyzing Modular Approaches for Visual Question Decomposition cs.CV · 2023 · author #2
  25. Uncovering Intermediate Variables in Transformers using Circuit Probing cs.CL · 2023 · author #3
  26. Emergence of Abstract State Representations in Embodied Sequence Modeling cs.LG · 2023 · author #6
  27. Characterizing Mechanisms for Factual Recall in Language Models cs.CL · 2023 · author #3
  28. Instilling Inductive Biases with Subnetworks cs.LG · 2023 · author #3
  29. Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations cs.CV · 2023 · author #7
  30. Circuit Component Reuse Across Tasks in Transformer Language Models cs.CL · 2023 · author #3
  31. NeuroSurgeon: A Toolkit for Subnetwork Analysis cs.LG · 2023 · author #2
  32. Language Models Implement Simple Word2Vec-style Vector Arithmetic cs.CL · 2023 · author #3
  33. Testing Causal Models of Word Meaning in GPT-3 and -4 cs.CL · 2023 · author #2
  34. Training Priors Predict Text-To-Image Model Performance cs.CV · 2023 · author #2
  35. Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs cs.LG · 2023 · author #3
  36. Comparing Trajectory and Vision Modalities for Verb Representation cs.CV · 2023 · author #3
  37. Break It Down: Evidence for Structural Compositionality in Neural Networks cs.CL · 2023 · author #3
  38. Are Language Models Worse than Humans at Following Prompts? It's Complicated cs.CL · 2023 · author #4
  39. Does CLIP Bind Concepts? Probing Compositionality in Large Image Models cs.CV · 2022 · author #7
  40. Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex cs.AI · 2022 · author #4
  41. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model cs.CL · 2022 · author #4
  42. Linearly Mapping from Image to Text Space cs.CL · 2022 · author #4
  43. Unit Testing for Concepts in Neural Networks cs.CL · 2022 · author #2
  44. Pretraining on Interactions for Learning Grounded Affordance Representations cs.CL · 2022 · author #4
  45. Do Trajectories Encode Verb Meaning? cs.CL · 2022 · author #3
  46. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models cs.CL · 2022 · author #125
  47. Do Vision-Language Pretrained Models Learn Composable Primitive Concepts? cs.CV · 2022 · author #3
  48. A Novel Corpus of Discourse Structure in Humans and Computers cs.CL · 2021 · author #8
  49. Does Vision-and-Language Pretraining Improve Lexical Grounding? cs.CL · 2021 · author #3
  50. Frequency Effects on Syntactic Rule Learning in Transformers cs.CL · 2021 · author #4
  51. Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color cs.CV · 2021 · author #5
  52. Do Prompt-Based Models Really Understand the Meaning of their Prompts? cs.CL · 2021 · author #2
  53. The MultiBERTs: BERT Reproductions for Robustness Analysis cs.CL · 2021 · author #12
  54. Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering cs.CL · 2021 · author #2
  55. Spatial Language Understanding for Object Search in Partially Observed City-scale Environments cs.RO · 2020 · author #4
  56. A Visuospatial Dataset for Naturalistic Verb Learning cs.CL · 2020 · author #2
  57. Measuring and Reducing Gendered Correlations in Pre-trained Models cs.CL · 2020 · author #6
  58. Self-play for Data Efficient Language Acquisition cs.CL · 2020 · author #2
  59. Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces cs.CL · 2020 · author #4
  60. Robot Object Retrieval with Contextual Natural Language Queries cs.RO · 2020 · author #5
  61. Does Data Augmentation Improve Generalization in NLP? cs.CL · 2020 · author #3
  62. What Happens To BERT Embeddings During Fine-tuning? cs.CL · 2020 · author #3
  63. Planning with State Abstractions for Non-Markovian Task Specifications cs.RO · 2019 · author #5
  64. What do you learn from context? Probing for sentence structure in contextualized word representations cs.CL · 2019 · author #11
  65. BERT Rediscovers the Classical NLP Pipeline cs.CL · 2019 · author #3
  66. Probing What Different NLP Tasks Teach Machines about Function Word Comprehension cs.CL · 2019 · author #12
  67. Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference cs.CL · 2019 · author #2
  68. Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling cs.CL · 2018 · author #15
  69. WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse cs.CL · 2018 · author #2
  70. Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation cs.CL · 2018 · author #5

Mentions

  • 2402.08674 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2310.09612 #7 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2508.05776 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2507.22457 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2507.03876 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2507.01790 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2505.20546 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2406.09519 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2502.07164 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2406.00053 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2311.04354 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2406.15955 #6 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2410.13984 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2410.09223 #5 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2212.10537 #7 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2310.08744 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2404.12444 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2305.16130 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2403.05576 #9 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2403.05534 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2402.08211 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2310.10899 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2311.06411 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2301.07085 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2311.02171 #6 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2301.10884 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2306.01755 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2310.15910 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2309.00244 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2211.05100 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2206.04615 #125 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2203.17271 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2305.14630 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2303.12737 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2303.08114 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2209.15162 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2211.14673 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2208.10244 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2207.02272 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2206.11953 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2109.01247 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2106.16163 #12 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2111.05940 #8 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2109.10246 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2109.07020 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2109.06129 #5 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2101.00391 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2012.02705 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2010.06032 #6 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2010.15225 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2010.02976 #4 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2010.04872 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2004.15012 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2006.13253 #5 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2004.14448 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1905.05950 #3 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1904.11544 #12 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1812.10860 #15 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1902.01007 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1905.12096 #5 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1905.06316 #11 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1804.08207 #5 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 1808.09422 #2 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2604.22027 #8 · arxiv_oai · confidence 0.70 Ellie Pavlick
  • 2405.14782 #22 · arxiv_oai · confidence 0.70 Ellie Pavlick

Frequent Coauthors