Co-Scale Conv-Attentional Image Transformers W Xu, Y Xu, TA Chang, Z Tu International Conference on Computer Vision, 2021 | 401 | 2021 |
Do Large Language Models Know What Humans Know? S Trott, C Jones, T Chang, J Michaelov, B Bergen Cognitive Science, 2023 | 95 | 2023 |
Language Model Behavior: A Comprehensive Survey TA Chang, BK Bergen Computational Linguistics, 2024 | 74 | 2024 |
Word Acquisition in Neural Language Models TA Chang, BK Bergen Transactions of the Association for Computational Linguistics 10, 1-16, 2022 | 47 | 2022 |
The Geometry of Multilingual Language Model Representations TA Chang, Z Tu, BK Bergen Conference on Empirical Methods in Natural Language Processing, 2022 | 44 | 2022 |
Distributional Semantics Still Can’t Account for Affordances CR Jones, TA Chang, S Coulson, JA Michaelov, S Trott, BK Bergen Annual Meeting of the Cognitive Science Society 44 (44), 2022 | 24 | 2022 |
Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models TA Chang, Y Xu, W Xu, Z Tu Annual Meeting of the Association for Computational Linguistics and the …, 2021 | 15 | 2021 |
When Is Multilinguality a Curse? Language Modeling for 250 High-and Low-Resource Languages TA Chang, C Arnett, Z Tu, BK Bergen Conference on Empirical Methods in Natural Language Processing, 2024 | 13 | 2024 |
Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models JA Michaelov, C Arnett, TA Chang, BK Bergen Conference on Empirical Methods in Natural Language Processing, 2023 | 10 | 2023 |
Encodings of Source Syntax: Similarities in NMT Representations Across Target Languages TA Chang, AN Rafferty 5th Workshop on Representation Learning for NLP at ACL, 2020 | 4 | 2020 |
Different Tokenization Schemes Lead to Comparable Performance in Spanish Number Agreement C Arnett, PD Rivière, TA Chang, S Trott SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and …, 2024 | 3 | 2024 |
Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability TA Chang, Z Tu, BK Bergen Transactions of the Association for Computational Linguistics, 2024 | 3 | 2024 |
Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models C Arnett, TA Chang, JA Michaelov, BK Bergen 3rd Multilingual Representation Learning Workshop at EMNLP, 2023 | 2 | 2023 |
Characterizing and Measuring Linguistic Dataset Drift TA Chang, K Halder, NA John, Y Vyas, Y Benajiba, M Ballesteros, D Roth Annual Meeting of the Association for Computational Linguistics, 2023 | 2 | 2023 |
Does Contextual Diversity Hinder Early Word Acquisition? TA Chang, BK Bergen Annual Meeting of the Cognitive Science Society 44 (44), 2022 | 2 | 2022 |
Goldfish: Monolingual Language Models for 350 Languages TA Chang, C Arnett, Z Tu, BK Bergen arXiv preprint arXiv:2408.10441, 2024 | 1 | 2024 |
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics TA Chang, K Tomanek, J Hoffmann, N Thain, E van Liemt, ... Joint International Conference on Computational Linguistics, Language …, 2024 | 1 | 2024 |
A Bit of a Problem: Measurement Disparities in Dataset Sizes Across Languages C Arnett, TA Chang, BK Bergen Annual Meeting of the Special Interest Group on Under-Resourced Languages at …, 2024 | 1 | 2024 |
Scalable Influence and Fact Tracing for Large Language Model Pretraining TA Chang, D Rajagopal, T Bolukbasi, L Dixon, I Tenney arXiv preprint arXiv:2410.17413, 2024 | | 2024 |
Correlations between Multilingual Language Model Geometry and Crosslingual Transfer Performance C Shah, Y Chandak, AM Mane, B Bergen, TA Chang Joint International Conference on Computational Linguistics, Language …, 2024 | | 2024 |