Related papers: Counterspeech the ultimate shield! Multi-Condition…

Social media are pervasive in our life, making it necessary to ensure safe online experiences by detecting and removing offensive and hate speech. In this work, we report our submission to the Offensive Language and hate-speech Detection…

Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a…

Tackling online hatred using informed textual responses - called counter narratives - has been brought under the spotlight recently. Accordingly, a research line has emerged to automatically generate counter narratives in order to…

Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. Although this method has proven to be effective for many domains, it might not always provide desirable…

Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of generating such examples are typically driven by local heuristic…

The pervasiveness of the Internet and social media have enabled the rapid and anonymous spread of Hate Speech content on microblogging platforms such as Twitter. Current EU and US legislation against hateful language, in conjunction with…

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

In recent years, monitoring hate speech and offensive language on social media platforms has become paramount due to its widespread usage among all age groups, races, and ethnicities. Consequently, there have been substantial research…

Hate Speech has become a major content moderation issue for online social media platforms. Given the volume and velocity of online content production, it is impossible to manually moderate hate speech related content on any platform. In…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Health misinformation spreading online poses a significant threat to public health. Researchers have explored methods for automatically generating counterspeech to health misinformation as a mitigation strategy. Existing approaches often…

Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions across the…

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically…

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain…

Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less commonly, methods have also been developed for binary…

This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…

In hate speech detection, developing training and evaluation datasets across various domains is the critical issue. Whereas, major approaches crawl social media texts and hire crowd-workers to annotate the data. Following this convention…

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the…

Hateful memes often require compositional multimodal reasoning: the image and text may appear benign in isolation, yet their interaction conveys harmful intent. Although thinking-based multimodal large language models (MLLMs) have recently…

State-of-the-art approaches for hate-speech detection usually exhibit poor performance in out-of-domain settings. This occurs, typically, due to classifiers overemphasizing source-specific information that negatively impacts its domain…