Challenge: Pre-trained language models (LMs) have grown substantially in both societal adoption and training costs.
Approach: They propose to use low-cost proxy models to democratise pre-model debiasing research by using small and mutable corpora.
Outcome: The proposed model can approximate bias acquisition and learning dynamics of larger models despite their reduced size.

Similar Papers

An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models inherit more human-like biases from the training corpora, causing computationally expensive problems.
Approach: They propose parameter-efficient methods in combination with counterfactual data augmentation for bias mitigation.
Outcome: The proposed methods are effective in mitigating gender bias, prompt tuning is more suitable for GPT-2 than BERT, and less effective when it comes to racial and religious bias.
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models (2023.acl-long)

Copied to clipboard

Challenge: Hundreds of studies have highlighted ethical issues in NLP models .
Approach: They propose to measure media biases in LMs trained on diverse data sources . they focus on hate speech and misinformation detection .
Outcome: The proposed methods quantify the fairness of downstream NLP models trained on politically biased LMs.
Debiasing Large Language Models with Structured Knowledge (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to reduce biases in pre-training models are hampered by their performance.
Approach: They propose a method that utilizes structured knowledge to mitigate bias in LLMs . their method obviates the need for training from scratch, thus offering enhanced scalability .
Outcome: The proposed method outperforms state-of-the-art (SOTA) baselines in the debiasing ability.
End-to-End Bias Mitigation by Modelling Biases in Corpora (2020.acl-main)

Copied to clipboard

Challenge: Recent studies have shown that strong natural language understanding models are prone to relying on unwanted dataset biases without learning the underlying task.
Approach: They propose two learning strategies to train neural models that are more robust to dataset biases and transfer better to out-of-domain datasets.
Outcome: The proposed methods improve robustness in all settings and transfer better to out-of-domain datasets.
Sustainable Modular Debiasing of Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing debiasing methods modify all of the PLM parameters, which is costly and leads to (catastrophic) forgetting of useful language knowledge.
Approach: They propose a modular debiasing approach based on dedicated adapters that inject adapter modules into the original PLM layers and update only the adapters.
Outcome: The proposed approach is based on dedicated adapters and retains fairness even after large-scale training.
Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing data-centric debiasing strategies mainly leverage explicit bias words for counterfactual data augmentation to balance the training data.
Approach: They propose a method which uses an explainability method to search for implicit bias words to assist in debiasing PLMs.
Outcome: Extensive results show that the proposed method achieves state-of-the-art debiasing performance and strong generalization while maintaining predictive abilities.
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings (2025.coling-main)

Copied to clipboard

Challenge: Existing work in this field has looked most commonly into gender bias, racial bias, and religious bias.
Approach: They propose an algorithm that uses a neural network to perform ‘soft debiasing’ and build on the seminal work of (CITATION) and (CitATION).
Outcome: The proposed algorithm outperforms current methods on gender, race, and religion metrics on a wide range of metrics.
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.
Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions (2023.acl-short)

Copied to clipboard

Challenge: Existing approaches to de-bias pre-trained large language models focus on changes to training regime, but this is not feasible.
Approach: They propose to de-bias a pre-trained model by fine-tuning it on only 10 examples . they show that the technique performs better than competitive baselines .
Outcome: The proposed method performs better than competitive state-of-the-art baselines with minimal loss in language modeling ability.
From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling (2025.findings-emnlp)

Copied to clipboard

Challenge: Current research on bias in language models focuses on data quality, not temporal influences of data.
Approach: They propose a methodology to interpret the interaction between training data and model architecture in bias propagation during language modeling.
Outcome: The proposed method analyzes the interaction between training data and model architecture in bias propagation during language modeling.

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