Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
Published in BlackboxNLP @ EMNLP 2021, 2021
Posts by Collection
publications
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Published in ACL 2022, 2022
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Published in ENLSP @ NeurIPS 2022, 2022
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
Published in ACL 2023, 2023
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
Published in BlackboxNLP @ EMNLP 2024, 2024
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
Published in KnowledgeFM @ ACL 2025, 2025