Challenge: Existing methods for subjective bias neutralization rely on parallel text training and lose important bias-independent context.
Approach: They propose a bias neutralization model that uses an auxiliary guided cycle consistent GAN to train with a combination of adversarial, cycleconsistency and identity mapping loss.
Outcome: The proposed model significantly improves subjective bias neutralization compared to existing methods.

Similar Papers

NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias (2022.naacl-main)

Copied to clipboard

Challenge: a new task is proposed to reduce media news framing bias by generating a neutral summary from multiple news articles of the varying political leanings.
Approach: They propose a task that generates a neutral summary from multiple news articles . they find title provides a good signal for framing bias and propose metric and model .
Outcome: The proposed task can neutralize news content in hierarchical order from title to article . scalability remains a bottleneck due to the time-consuming human labor needed for composing the roundup .
WIKIBIAS: Detecting Multi-Span Subjective Biases in Language (2021.findings-emnlp)

Copied to clipboard

Challenge: a particular type of bias is subjective bias, which introduces improper attitudes or presents a statement with the presupposition of truth.
Approach: They propose to annotate a Wikipedia edits corpus with 4,000 sentence pairs to detect subjective bias.
Outcome: The proposed dataset can be used as a research benchmark and generalize to multiple domains.
Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training (N19-1)

Copied to clipboard

Challenge: Recent work has shown superior performance for non-adversarial methods in more challenging language pairs.
Approach: They propose to use adversarial autoencoder to map monolingual embeddings to a shared space and to put the target encoders as an adversary against the corresponding discriminator.
Outcome: The proposed method is more robust and achieves better performance than previously proposed adversarial and non-adversarial methods.
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training (2020.emnlp-main)

Copied to clipboard

Challenge: Neural models pick up on annotation artefacts and spurious correlations, resulting in learning sentences that suffer from the same biases.
Approach: They propose to tackle this problem by using adversarial training to reduce the bias in sentence representations by using an ensemble of adversaries.
Outcome: The proposed approach produces more robust models outperforming previous de-biasing efforts when generalised to 12 other NLI datasets.
Balancing out Bias: Achieving Fairness Through Balanced Training (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to reducing group bias do not account for correlations between author demographics and linguistic variables, limiting their effectiveness.
Approach: They extend a method for countering group bias using balanced training by balancing each demographic group in training and using protected attributes as input.
Outcome: The proposed model outperforms all other methods when combined with balanced training.
BiasFilter: An Inference-Time Debiasing Framework for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for debiasing large language models incur high human and computational costs and are limited in their effectiveness.
Approach: They propose a model-agnostic, inference-time debiasing framework that enforces fairness by filtering generation outputs in real time.
Outcome: The proposed framework mitigates social bias across a range of LLMs while preserving overall generation quality.
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 .
Improving Bias Mitigation through Bias Experts in Natural Language Understanding (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to mitigate the detrimental effect of bias on the network include debiasing methods that down-weight the biased examples identified by an auxiliary model, which is trained with explicit bias labels.
Approach: They propose a framework that introduces binary classifiers between the auxiliary model and main model, coined bias experts, to reduce the detrimental effect of bias on the network.
Outcome: The proposed approach outperforms the state-of-the-art on various datasets while achieving high performance on in-distribution data.
NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives (2021.emnlp-main)

Copied to clipboard

Challenge: Recent years have seen an increasing need for gender-neutral and inclusive language.
Approach: They propose a rule-based and a neural approach to gender-neutral rewriting for English . they use manually curated synthetic and natural data to train a rewriter .
Outcome: The proposed approach improves on the rule-based approach with word error rates below 0.18% on synthetic, in-domain and out-domain test sets.
It’s All Relative: Learning Interpretable Models for Scoring Subjective Bias in Documents from Pairwise Comparisons (2024.eacl-long)

Copied to clipboard

Challenge: a new model to score subjective bias in documents is developed to perform pairwise comparisons . a recent study shows that the model can be explained and validated for other domains based on the training data.
Approach: They propose an interpretable model to score subjective bias in Wikipedia articles . they train the model on pairs of revisions of the same Wikipedia article .
Outcome: The proposed model can interpret parameters to discover words most indicative of bias . it compares legal texts, news media and law amendments in three settings .

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