Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck

1 code implementation • 30 Oct 2023 • Josh Magnus Ludan, Qing Lyu, Yue Yang, Liam Dugan, Mark Yatskar, Chris Callison-Burch

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability.

Language Modelling Large Language Model +2

Explanation-based Finetuning Makes Models More Robust to Spurious Cues

1 code implementation • 8 May 2023 • Josh Magnus Ludan, Yixuan Meng, Tai Nguyen, Saurabh Shah, Qing Lyu, Marianna Apidianaki, Chris Callison-Burch

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data.