Title |
|---|
Word Form Matters: LLMs' Semantic Reconstruction under TypoglycemiaAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency ParsingAAAI Conference on Artificial Intelligence (AAAI), 2025 |
 |
 Mission: Impossible Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural
Scrambled TextConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Unnatural language processing: How do language models handle
machine-generated prompts?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Unsupervised Dialogue Topic Segmentation in Hyperdimensional SpaceInterspeech (Interspeech), 2023 |
 Dissecting Multimodality in VideoQA Transformer Models by Impairing
Modality FusionInternational Conference on Machine Learning (ICML), 2023 |
 Towards preserving word order importance through Forced InvalidationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 |
 Audio-Text Models Do Not Yet Leverage Natural LanguageIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 On the Blind Spots of Model-Based Evaluation Metrics for Text GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 CREPE: Can Vision-Language Foundation Models Reason Compositionally?Computer Vision and Pattern Recognition (CVPR), 2022 |
 Detecting Languages Unintelligible to Multilingual Models through Local
Structure ProbesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Word Order Matters when you Increase MaskingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Why is Winoground Hard? Investigating Failures in Visuolinguistic
CompositionalityConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence
EmbeddingConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 When and why vision-language models behave like bags-of-words, and what
to do about it?International Conference on Learning Representations (ICLR), 2022 |
 Shortcut Learning of Large Language Models in Natural Language
UnderstandingCommunications of the ACM (CACM), 2022 |
 Compositional Evaluation on Japanese Textual Entailment and SimilarityTransactions of the Association for Computational Linguistics (TACL), 2022 |
 The Role of Complex NLP in Transformers for Text Ranking?International Conference on the Theory of Information Retrieval (ICTIR), 2022 |
 Can language models learn from explanations in context?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Word Order Does Matter (And Shuffled Language Models Know It)Annual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 When classifying grammatical role, BERT doesn't care about word order...
except when it mattersAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Oolong: Investigating What Makes Transfer Learning Hard with Controlled
StudiesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Neural reality of argument structure constructionsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Variation and generality in encoding of syntactic anomaly information in
sentence embeddingsBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2021 |
