Related papers: CO-STAR: Conceptualisation of Stereotypes for Anal…
Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing…
Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning.…
We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener and context. We argue that reasoning is crucial for…
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…
Accurately measuring gender stereotypical bias in language models is a complex task with many hidden aspects. Current benchmarks have underestimated this multifaceted challenge and failed to capture the full extent of the problem. This…
Social media platforms provide users the freedom of expression and a medium to exchange information and express diverse opinions. Unfortunately, this has also resulted in the growth of abusive content with the purpose of discriminating…
Memes act as cryptic tools for sharing sensitive ideas, often requiring contextual knowledge to interpret. This makes moderating multimodal memes challenging, as existing works either lack high-quality datasets on nuanced hate categories or…
Hate speech has grown significantly on social media, causing serious consequences for victims of all demographics. Despite much attention being paid to characterize and detect discriminatory speech, most work has focused on explicit or…
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this…
Coherent discourse is distinguished from a mere collection of utterances by the satisfaction of a diverse set of constraints, for example choice of expression, logical relation between denoted events, and implicit compatibility with…
Implicit hate speech has recently emerged as a critical challenge for social media platforms. While much of the research has traditionally focused on harmful speech in general, the need for generalizable techniques to detect veiled and…
Numerous datasets have been proposed to combat the spread of online hate. Despite these efforts, a majority of these resources are English-centric, primarily focusing on overt forms of hate. This research gap calls for developing…
A proven therapeutic technique to overcome negative thoughts is to replace them with a more hopeful "reframed thought." Although therapy can help people practice and learn this Cognitive Reframing of Negative Thoughts, clinician shortages…
As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently…
This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised…
Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…
The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is…
Hate speech detection on social media faces challenges in both accuracy and explainability, especially for underexplored Indic languages. We propose a novel explainability-guided training framework, X-MuTeST (eXplainable Multilingual haTe…
Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently…
The i* modeling language was introduced to fill the gap in the spectrum of conceptual modeling languages, focusing on the intentional (why?), social (who?), and strategic (how? how else?) dimensions. i* has been applied in many areas, e.g.,…