Related papers: Mimicking How Humans Interpret Out-of-Context Sent…

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…

Providing explanations along with predictions is crucial in some text processing tasks. Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence…

Language models are known to produce vague and generic outputs. We propose two unsupervised decoding strategies based on either word-frequency or point-wise mutual information to increase the specificity of any model that outputs a…

Internet memes are a powerful form of online communication, yet their nature and reliance on commonsense knowledge make toxicity detection challenging. Identifying key features for meme interpretation and understanding, is a crucial task.…

State-of-the-art image captioners can generate accurate sentences to describe images in a sequence to sequence manner without considering the controllability and interpretability. This, however, is far from making image captioning widely…

Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework…

Large language models produce human-like text that drive a growing number of applications. However, recent literature and, increasingly, real world observations, have demonstrated that these models can generate language that is toxic,…

Sentence simplification aims to make sentences easier to read and understand. Recent approaches have shown promising results with sequence-to-sequence models which have been developed assuming homogeneous target audiences. In this paper we…

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 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,…

In this introductory article we present the basics of an approach to implementing computational interpreting of natural language aiming to model the meanings of words and phrases. Unlike other approaches, we attempt to define the meanings…

When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities. If we humans cannot figure out the meaning of those…

With the increasing influence of social media, online misinformation has grown to become a societal issue. The motivation for our work comes from the threat caused by cheapfakes, where an unaltered image is described using a news caption in…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to…

Online toxic content has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. A significant amount of research has been focused on detecting or analyzing toxic content using machine-learning…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that…

Speech-acts can have literal meaning as well as pragmatic meaning, but these both involve consequences typically intended by a speaker. Speech-acts can also have unintentional meaning, in which what is conveyed goes above and beyond what…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…