paper-with-me

Papers

Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis

2023-05-23 · Oscar Chew, Hsuan-Tien Lin, Kai-Wei Chang, Kuan-Hao Huang

Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classifier may erroneously learn that the token "performances" is commonly associated with positive movie reviews. Relying on these spurious correlations degrades the classifiers performance when it deploys on out-of-distribution data. In this paper, we examine the implications of spurious correlations through a novel perspective called neighborhood analysis. The analysis uncovers how spurious correlations lead unrelated words to erroneously cluster together in the embedding space. Driven by the analysis, we design a metric to detect spurious tokens and also propose a family of regularization methods, NFL (doN't Forget your Language) to mitigate spurious correlations in text classification. Experiments show that NFL can effectively prevent erroneous clusters and significantly improve the robustness of classifiers without auxiliary data. The code is publicly available at https://github.com/oscarchew/doNt-Forget-your-Language.

📄 PDF Abstract BibTeX arXiv:2305.13654

Code (1)

oscarchew/dont-forget-your-language 공식 구현 pytorch

Tasks

Classificationtext-classificationText Classification

Similar Papers 제목 키워드 기반

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

2024-11-06 · Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari 외

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…

image-classificationImage Classificationzero-shot-classificationZero-Shot Learning

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

2023-11-15 · YuHang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An 외

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness…

counterfactualIn-Context Learningtext-classificationText Classification

MaskTune: Mitigating Spurious Correlations by Forcing to Explore

2022-09-30 · Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani, Ali Gholami 외

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work prop…

Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese

2023-08-25 · Angana Borah, Daria Pylypenko, Cristina Espana-Bonet, Josef van Genabith

Recent work has shown evidence of 'Clever Hans' behavior in high-performance neural translationese classifiers, where BERT-based classifiers capitalize on spurious correlations, in particular topic information, between d…

Classification

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference

2024-04-22 · Yujin Han, Difan Zou

Standard empirical risk minimization (ERM) models may prioritize learning spurious correlations between spurious features and true labels, leading to poor accuracy on groups where these correlations do not hold. Mitigati…

Attribute