Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers

26 May 2023

Papers citing "Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers"

10 / 10 papers shown

Title
CASCADE Your Datasets for Cross-Mode Knowledge Retrieval of Language Models Runlong Zhou Yi Zhang RALM 53 0 0 02 Apr 2025
Estimating Causal Effects of Text Interventions Leveraging LLMs Siyi Guo Myrl G. Marmarelis Fred Morstatter Kristina Lerman CML 52 0 0 28 Oct 2024
Hate Speech Detection with Generalizable Target-aware Fairness Tong Chen Danny Wang Xurong Liang Marten Risius Gianluca Demartini Hongzhi Yin 17 3 0 28 May 2024
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis Oscar Chew Hsuan-Tien Lin Kai-Wei Chang Kuan-Hao Huang 22 5 0 23 May 2023
Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens Nitish Joshi X. Pan Hengxing He CML 42 28 0 25 Oct 2022
NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation Phillip Howard Gadi Singer Vasudev Lal Yejin Choi Swabha Swayamdipta CML 48 25 0 22 Oct 2022
Diversify and Disambiguate: Learning From Underspecified Data Yoonho Lee Huaxiu Yao Chelsea Finn 203 64 0 07 Feb 2022
Linear Adversarial Concept Erasure Shauli Ravfogel Michael Twiton Yoav Goldberg Ryan Cotterell KELM 71 56 0 28 Jan 2022
Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models Tianlu Wang Rohit Sridhar Diyi Yang Xuezhi Wang AAML 108 70 0 14 Oct 2021
An Investigation of Why Overparameterization Exacerbates Spurious Correlations Shiori Sagawa Aditi Raghunathan Pang Wei Koh Percy Liang 144 368 0 09 May 2020