Related papers: Simple Text Detoxification by Identifying a Linear…
Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…
Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as…
We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the…
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…
The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful…
Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…
Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…
Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…
Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network models gaining increasing popularity is structured state space…
Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…
To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. Recognizing this research gap,…
The incorporation of Denoising Diffusion Models (DDMs) in the Text-to-Speech (TTS) domain is rising, providing great value in synthesizing high quality speech. Although they exhibit impressive audio quality, the extent of their semantic…
Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…
Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms. This study proposes a joint retrieval framework…
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…
Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have…
Large language models are trained on vast amounts of internet data, prompting concerns and speculation that they have memorized public benchmarks. Going from speculation to proof of contamination is challenging, as the pretraining data used…
We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that…
Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches…
Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon is pervasive and consistent across different word embedding…