Perturbation Sensitivity Analysis to Detect Unintended Model Biases (D19-1)

Copied to clipboard

Challenge: Recent research shows that data-driven NLP models may inadvertently capture, reflect and sometimes amplify various social biases present in the language data they are trained on.
Approach: They propose a generic evaluation framework that detects unintended model biases related to named entities and requires no new annotations or corpora.
Outcome: The proposed framework detects unintended model biases related to named entities and requires no new annotations or corpora.

Similar Papers

Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies show that NLP models are vulnerable to adversarial perturbations such as synonym substitutions or syntax-guided paraphrasing.
Approach: They propose a “double perturbation” framework to uncover model weaknesses beyond the test dataset.
Outcome: The proposed attack achieves high success rates on both original and robustly trained CNNs and Transformers.
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview (2020.acl-main)

Copied to clipboard

Challenge: a growing number of studies address the effect of bias on predictions, but no unifying framework exists . a general phenomenon of biased predictive models in NLP is not recent, authors say .
Approach: They propose a unifying framework for identifying and reducing bias in natural language processing . they propose to differentiate two consequences of bias and four potential origins of bias .
Outcome: The proposed framework provides an overview of predictive bias in natural language processing . it differentiates two consequences of bias and four potential origins of bias: label bias, selection bias, model overamplification, and semantic bias.
BiasWipe: Mitigating Unintended Bias in Text Classifiers through Model Interpretability (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to mitigate unintended bias in social media platforms are re-training and adding extra parameters to the model.
Approach: They propose a technique to mitigate unintended bias in language models by pruning the neuron weights responsible for univ bias.
Outcome: The proposed technique achieves fairness by pruning the neuron weights responsible for unintended bias without loss of original performance.
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation (2020.findings-emnlp)

Copied to clipboard

Challenge: Language modeling has advanced rapidly due to efficient model architectures and the availability of large text corpora.
Approach: They propose to embed and regularize sentiment prediction-derived regularizations on the language model’s latent representations to reduce bias in the sentiment of generated text.
Outcome: The proposed methods reduce bias in the sentiment of generated text by adopting individual and group fairness metrics from the fair machine learning literature.
Are Text Classifiers Xenophobic? A Country-Oriented Bias Detection Method with Least Confounding Variables (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for detecting biases are biased because of confounding variables . authors propose a method to detect the biased classifier on any type of unlabeled data .
Approach: They propose a method to detect biases of a specific fine-tuned classifier on unlabeled data.
Outcome: The proposed method detects biases on unlabeled data on named entity perturbations . it uses name-entity recognition on target-domain data and morphosynctactically different languages spoken in relation to countries of the target groups .
Perturbed examples reveal invariances shared by language models (2024.findings-acl)

Copied to clipboard

Challenge: Rapid growth in natural language processing (NLP) research has led to numerous new models outpacing our understanding of how they compare to established ones.
Approach: They propose a framework to compare two NLP models by revealing their shared invariance to interpretable input perturbations targeting a specific linguistic capability.
Outcome: The proposed framework can shed light on the types of invariances retained or emerging in new models.
On Measures of Biases and Harms in NLP (2022.findings-aacl)

Copied to clipboard

Challenge: Recent studies show that natural language processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Approach: They propose a framework for harms and questions to help practitioners understand biases . they propose measurable measures to detect and mitigate biased groups .
Outcome: The proposed framework provides a framework for harms and questions for practitioners to answer to guide the development of bias measures.
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP (2021.tacl-1)

Copied to clipboard

Challenge: Pretrained language models pick up and reproduce undesirable biases when trained on large, unfiltered crawls from the Internet.
Approach: They propose a decoding algorithm that, given only a textual description of the undesired behavior, reduces the probability of a language model producing problematic text.
Outcome: The proposed approach reduces the probability of a language model producing problematic text by giving only a textual description of the undesired behavior.
ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations (2024.emnlp-main)

Copied to clipboard

Challenge: Existing large language models struggle with systematically perturbed data designed to evade detection mechanisms.
Approach: They propose a large language model with homophonic substitutions and emoji transformations to test their models' robustness against cloaking perturbations.
Outcome: The proposed model underperforms in detecting offensive content when perturbations are applied to Chinese language datasets.
It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations (2020.acl-main)

Copied to clipboard

Challenge: Existing work on societal bias in NLP focuses on race and gender . linguistic background is a unique attribute that has been largely ignored in the field .
Approach: They examine linguistic background to craft plausible adversarial examples that expose biases in popular NLP models.
Outcome: The proposed model improves robustness without sacrificing performance on clean data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations