Challenge: Using pre-trained language models, we evaluate performance group disparities while none of these techniques guarantee fairness, nor consistently mitigate group disparity.
Approach: They present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks.
Outcome: The proposed methods show that performance group disparities are vibrant in many cases, while none of these techniques guarantee fairness, nor consistently mitigate group disparity.

Similar Papers

Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal NLP (2025.acl-long)

Copied to clipboard

Challenge: a recent study shows that models often make less reliable or overconfident predictions for marginalized groups.
Approach: They evaluate performance and reliability disparities across demographic, regional, and legal attributes across four jurisdictions using the FairLex benchmark.
Outcome: The FairLex benchmark shows that pre-training improves performance and reliability for underrepresented groups.
Are Pretrained Multilingual Models Equally Fair across Languages? (2022.coling-1)

Copied to clipboard

Challenge: Pretrained multilingual language models can help bridge the digital language divide, enabling high-quality NLP models for lower-resourced languages.
Approach: They propose to use a multilingual dataset to examine whether multilingual models are equally fair across languages.
Outcome: The proposed model enables apples-to-apples comparison across languages of group disparities in multilingual language models.
Fairness in Language Models Beyond English: Gaps and Challenges (2023.findings-eacl)

Copied to clipboard

Challenge: Language models are inequitable at encoding and re-presentation, but there is much to be studied and criticism for the existing research that remains to be addressed.
Approach: They propose to survey fairness in multilingual and non-English contexts . they argue that it is infeasible to achieve comprehensive coverage in terms of fairness datasets based on English .
Outcome: The proposed methods are infeasible to scale across languages and cultures, the authors argue . they argue that the current methods are too narrowly focused on specific dimensions and types of biases and cannot scale across cultures.
Assessing Multilingual Fairness in Pre-trained Multimodal Representations (2022.findings-acl)

Copied to clipboard

Challenge: Recent pre-trained multimodal models have shown exceptional capabilities towards connecting images and natural language.
Approach: They propose two new fairness notions for pre-trained multimodal models that consider language as the fairness recipient.
Outcome: The proposed models can be generalized to multilingualism by cross-lingual alignment . the results show that the models are individually fair across languages .
LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in legal NLP have led to a rapid growth of the field . however, many benchmarks are available only in English and no multilingual benchmark exists .
Approach: They propose to use 11 datasets covering 24 languages to compare NLP models.
Outcome: The proposed benchmarks show that even the best baseline only achieves modest results and ChatGPT struggles with many tasks.
Bias and Fairness in Natural Language Processing (D19-2)

Copied to clipboard

Challenge: a tutorial will review the history of bias and fairness studies in machine learning and language processing .
Approach: This tutorial reviews the history of bias and fairness studies in machine learning and language processing . it presents recent community effort to quantify and mitigat bias in natural language processing models .
Outcome: This tutorial reviews the history of bias and fairness studies in machine learning and language processing . it aims to quantify and mitigate bias in natural language processing models for a wide spectrum of tasks .
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English (2022.acl-long)

Copied to clipboard

Challenge: Laws and their interpretations, legal arguments and agreements are typically expressed in writing.
Approach: They propose a benchmark to evaluate model performance across legal NLU tasks . they also evaluate several generic and legal-oriented models .
Outcome: The proposed model performs better across multiple tasks than previous models.
Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models (2022.naacl-main)

Copied to clipboard

Challenge: An increasing awareness of biased patterns in natural language processing resources such as BERT has motivated many metrics to quantify ‘bias’ and ‘fairness’.
Approach: They combine literature survey, correlation analysis and empirical evaluations to evaluate compatibility of fairness metrics for pre-trained language models and their downstream tasks.
Outcome: The proposed measures are not compatible with each other and highly depend on (i) templates, (ii) attribute and target seeds and (iv) the choice of embeddings.
Benchmarking Intersectional Biases in NLP (2022.naacl-main)

Copied to clipboard

Challenge: Recent work on fairness of machine learning models has focused on how to debias, but research on the fairness and performance of biased/debiased models on downstream prediction tasks has been limited.
Approach: They assess intersectional bias - fairness across multiple demographic dimensions . they highlight possible causes and make recommendations for future NLP debiasing research.
Outcome: The proposed approaches fare well in terms of fairness-accuracy trade-off, but are unable to effectively alleviate bias in downstream tasks.
Your fairness may vary: Pretrained language model fairness in toxic text classification (2022.findings-acl)

Copied to clipboard

Challenge: Pre-trained, bidirectional language models have revolutionized natural language processing research . authors show that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics .
Approach: They propose to use two post-processing methods to improve model fairness without retraining . they use pretrained language models of varying sizes on two toxic text classification tasks .
Outcome: The proposed methods improve model fairness without retraining . the results show that the fairness variation is more than just accuracy .

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