Related papers: Detoxifying Language Models with a Toxic Corpus

Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings. In parallel, these improvements have prompted a heated discourse around the risks of…

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Condescending language use is caustic; it can bring dialogues to an end and bifurcate communities. Thus, systems for condescension detection could have a large positive impact. A challenge here is that condescension is often impossible to…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

Verbal deception has been studied in psychology, forensics, and computational linguistics for a variety of reasons, like understanding behaviour patterns, identifying false testimonies, and detecting deception in online communication.…

With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have…

We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models…

Warning: this paper contains model outputs exhibiting offensiveness and biases. Recently pre-trained language models (PLMs) have prospered in various natural language generation (NLG) tasks due to their ability to generate fairly fluent…

Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CAUSALDETOX, a…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

The field of natural language generation has witnessed significant advancements in recent years, including the development of controllable text generation techniques. However, controlling the attributes of the generated text remains a…

We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo,…

Large pretrained language models can easily produce toxic or biased content, which is prohibitive for practical use. In order to detect such toxic generations, existing methods rely on templates, real-world data extraction, crowdsourcing…

Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also…

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing…

Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on…

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which…