BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification

Pub Date : 2022-12-10 DOI: 10.48550/arXiv.2212.05327 Ruixuan Tang, Hanjie Chen, Yangfeng Ji

Intermediate Entity-based Sparse Interpretable Representation Learning

Pub Date : 2022-12-03 DOI: 10.48550/arXiv.2212.01641 Diego Garcia-Olano, Yasumasa Onoe, J. Ghosh, Byron C. Wallace

On the Compositional Generalization Gap of In-Context Learning

Pub Date : 2022-11-15 DOI: 10.48550/arXiv.2211.08473 Arian Hosseini, A. Vani, Dzmitry Bahdanau, Alessandro Sordoni, Aaron C. Courville