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.

Similar Papers

Leveraging Pre-trained Language Models for Gender Debiasing (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to reduce gender bias in natural language are costly and time-consuming.
Approach: They propose a method to generate gender variants for a given text using pre-trained language models as the resource without any task-specific labelled data.
Outcome: The proposed method can reduce gender bias in a language generation context without a task-specific labelled data.
Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for debiasing are resource-intensive and costly. Existing solutions for debiansing require fine-tuning on downstream tasks.
Approach: They propose to integrate Masked Language Modeling (MLM) training objectives into fine-tuning’s training process to debiase the PLMs.
Outcome: The proposed approach outperforms the state-of-the-art baselines in terms of gender bias scores while improving PLMs’ performance solely using the downstream tasks’ dataset.
Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function (P19-2)

Copied to clipboard

Challenge: Existing methods to reduce gender bias in natural language datasets are inadequate.
Approach: They propose a loss function modification approach which equalizes the probabilities of male and female words in the output.
Outcome: The proposed approach outperforms existing methods in several aspects, especially in reducing gender bias in occupation words.
Reducing Gender Bias in Abusive Language Detection (D18-1)

Copied to clipboard

Challenge: Abusive language detection models tend to be biased toward identity words of a certain group of people . recent studies have raised concerns about the robustness of such systems .
Approach: They propose to use debiased word embeddings, gender swap data augmentation to reduce model bias . they also propose to fine-tune models with a larger corpus to correct such bias if needed .
Outcome: The proposed methods reduce model bias by 90-98% and can be extended to correct model bias in other scenarios.
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.
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.
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.
Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model (2023.acl-long)

Copied to clipboard

Challenge: Existing work has explored using sequence-to-sequence rewriting models to transform biased outputs into more gender-fair language by creating pseudo training data through linguistic rules.
Approach: They propose to use machine translation models to create gender-biased text from real gender-fair text via round-trip translation to eliminate rule-based data creation.
Outcome: The proposed approach matches the performance of state-of-the-art rewriting models for English.
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.

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