Related papers: Self-Diagnosis and Self-Debiasing: A Proposal for …

The training of large language models (LLMs) on extensive, unfiltered corpora sourced from the internet is a common and advantageous practice. Consequently, LLMs have learned and inadvertently reproduced various types of biases, including…

Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods…

Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have been proposed, which are primarily categorized into…

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…

As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Debiasing methods that seek to mitigate the tendency of Language Models (LMs) to occasionally output toxic or inappropriate text have recently gained traction. In this paper, we propose a standardized protocol which distinguishes methods…

Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and…

Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. In spite of the increasing accuracy, current data-driven approaches could easily learn biases from the imbalanced data…

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases…

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with…

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Probing or fine-tuning (large-scale) pre-trained models results in state-of-the-art performance for many NLP tasks and, more recently, even for computer vision tasks when combined with image data. Unfortunately, these approaches also entail…