Challenge: Prior work identifies a linear gender subspace and removes gender information by eliminating the subspace.
Approach: They propose to use DensRay to obtain interpretable dense subspaces by applying it to attention heads and layers of BERT.
Outcome: The proposed method performs on-par with prior approaches, but is more robust and preserves language model performance better.

Similar Papers

Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to evaluate gender bias in PLMs focus on one label out of three labels, such as neutral.
Approach: They propose a bias evaluation method for PLMs that considers all the three labels of NLI task and then defines a measure based on the corresponding label output.
Outcome: The proposed method can distinguish biased, incorrect inferences from non-biased incorrect infertility better than baseline, resulting in a more accurate bias evaluation.
Identifying and Reducing Gender Bias in Word-Level Language Models (N19-3)

Copied to clipboard

Challenge: Existing discriminatory biases in training data can be amplified by models . text corpora exhibit socially problematic biase .
Approach: They propose a metric to measure gender bias and a regularization loss term to minimize embeddings onto an embeddable subspace that encodes gender.
Outcome: The proposed method reduces gender bias up to an optimal weight assigned to the loss term, and the model becomes unstable as the perplexity increases.
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.
In-Contextual Gender Bias Suppression for Large Language Models (2024.findings-eacl)

Copied to clipboard

Challenge: Prior work has proposed debiasing methods that require human labelled examples, data augmentation and fine-tuning of LLMs, which are computationally expensive.
Approach: They propose to suppress gender biases by providing textual preambles from manually designed templates and real-world statistics without accessing model parameters.
Outcome: The proposed methods suppress gender biases in English LLMs using a CrowsPairs dataset without accessing model parameters.
UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts (2024.eacl-srw)

Copied to clipboard

Challenge: Language models (LMs) often include societal biases encoded in the human-produced datasets used for their training.
Approach: They evaluated six prominent language models: BERT, RoBERTa, DistilBERT, BERT- multilingual, XLM-RoBERT and DistilberT- multilinguistic.
Outcome: The results show that the models generated by the models were stereotypically gendered and with a reduced bias in multilingual variants.
An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language Models (2022.findings-naacl)

Copied to clipboard

Challenge: Pretrained language models (PLMs) have been shown to encapsulate social biases, including those relating to gender and race.
Approach: They propose a new bias measure based on Jensen–Shannon divergence that retains more information from the model output probabilities than other previously proposed bias measures.
Outcome: The proposed measure outperforms CrowS-Pairs and other similar measures for non-English datasets.
On Evaluating and Mitigating Gender Biases in Multilingual Settings (2023.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks and resources for evaluating gender biases in multilingual settings are limited.
Approach: They propose to extend DisCo to different Indian languages using human annotations to evaluate gender biases in multilingual models.
Outcome: The proposed benchmarks and mitigation techniques are extended beyond English to evaluate gender biases in multilingual models.
Gender-preserving Debiasing for Pre-trained Word Embeddings (P19-1)

Copied to clipboard

Challenge: Existing methods for debiasing word embeddings have shown discriminative biases . word embeds learnt from social media have shown to encode racist, offensive and discriminative language usage.
Approach: They propose a method that preserves gender-related information while removing stereotypical gender biases from pre-trained word embeddings.
Outcome: The proposed method preserves gender-related information while removing stereotypical discriminative gender biases from pre-trained word embeddings.
Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined.
Approach: They propose a standard domain adaptation model to reduce gender bias in multilingual contexts.
Outcome: The proposed model reduces gender bias and improves on two text classification tasks with three fair-aware baselines.
Projective Methods for Mitigating Gender Bias in Pre-trained Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Mitigating gender bias in NLP has a long history tied to debiasing static word embeddings.
Approach: They propose a masked language modelling task where content is developed around known social stereotypes and a projective debiasing method is used to reduce bias.
Outcome: The proposed methods reduce intrinsic bias and mitigat observed bias in a downstream setting, but the two outcomes are not necessarily correlated.

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