Title |
|---|
 Toward Neurosymbolic Program ComprehensionIEEE International Conference on Program Comprehension (ICPC), 2025 |
 Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference ResolutionWorkshop on Representation Learning for NLP (RepL4NLP), 2025 |
 Gumbel Counterfactual Generation From Language ModelsInternational Conference on Learning Representations (ICLR), 2024 |
 The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based
Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Mechanistic?BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2024 |
 Don't Stop Me Now: Embedding Based Scheduling for LLMsInternational Conference on Learning Representations (ICLR), 2024 |
 When Parts are Greater Than Sums: Individual LLM Components Can
Outperform Full ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 What does the Knowledge Neuron Thesis Have to do with Knowledge?International Conference on Learning Representations (ICLR), 2024 |
 MuLan: A Study of Fact Mutability in Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 Adjusting Interpretable Dimensions in Embedding Space with Human
JudgmentsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 Katrin Erk Marianna Apidianaki |
 On Linearizing Structured Data in Encoder-Decoder Language Models:
Insights from Text-to-SQLNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
