Related papers: Mitigating harm in language models with conditiona…

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…

Text classification is an important topic in the field of natural language processing. It has been preliminarily applied in information retrieval, digital library, automatic abstracting, text filtering, word semantic discrimination and many…

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

In this paper, we explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. First, we investigate how useful a pre-trained language model would be in a 2-step pipeline…

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning…

We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP…

Detecting persuasion in argumentative text is a challenging task with important implications for understanding human communication. This work investigates the role of persuasion strategies - such as Attack on reputation, Distraction, and…

The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, faked or forged content. In response, various proposals have…

This paper calls on the research community not only to investigate how human biases are inherited by large language models (LLMs) but also to explore how these biases in LLMs can be leveraged to make society's "unwritten code" - such as…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard…

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Predicting highly-cited papers is a long-standing challenge due to the complex interactions of research content, scholarly communities, and temporal dynamics. Recent advances in large language models (LLMs) raise the question of whether…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Social media communication has become a significant part of daily activity in modern societies. For this reason, ensuring safety in social media platforms is a necessity. Use of dangerous language such as physical threats in online…

Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given…

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data,…

The World Wide Web provides unrivalled access to information globally, including factual news reporting and commentary. However, state actors and commercial players increasingly spread biased (distorted) or fake (non-factual) information to…

Current approaches to reducing undesired capabilities in language models are largely post hoc, and can thus be easily bypassed by adversaries. A natural alternative is to shape capabilities during pretraining itself. On the proxy task of…

Standard language model evaluations can fail to capture risks that emerge only at deployment scale. For example, a model may produce safe responses during a small-scale beta test, yet reveal dangerous information when processing billions of…