Related papers: Concept-Based Interpretability for Toxicity Detect…
Contextual Bandits find important use cases in various real-life scenarios such as online advertising, recommendation systems, healthcare, etc. However, most of the algorithms use flat feature vectors to represent context whereas, in the…
Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, differences in user and system terminologies can challenge the identification of the user's information needs, and…
Generic `toxicity' classifiers continue to be used for evaluating the potential for harm in natural language generation, despite mounting evidence of their shortcomings. We consider the challenge of measuring misogyny in natural language…
Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful content. To mitigate these risks, post-hoc model intervention…
Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions. However, concerns have been raised about the potential for these models to create content that infringes on…
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…
Concepts benefit natural language understanding but are far from complete in existing knowledge graphs (KGs). Recently, pre-trained language models (PLMs) have been widely used in text-based concept extraction (CE). However, PLMs tend to…
Augmenting toxic language data in a controllable and class-specific manner is crucial for improving robustness in toxicity classification, yet remains challenging due to limited supervision and distributional skew. We propose ToxiGAN, a…
Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients…
Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…
Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…
Toxic language is difficult to define, as it is not monolithic and has many variations in perceptions of toxicity. This challenge of detecting toxic language is increased by the highly contextual and subjectivity of its interpretation,…
Toxicity is a prevalent social behavior that involves the use of hate speech, offensive language, bullying, and abusive speech. While text-based approaches for toxicity detection are common, there is limited research on processing speech…
Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification…
Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to explain models' decision. Recent works proposed to utilize Large…
As toxic language becomes nearly pervasive online, there has been increasing interest in leveraging the advancements in natural language processing (NLP), from very large transformer models to automatically detecting and removing toxic…
The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two key challenges emerge: 1) the absence of domain-specific…
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been…
Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict concepts and then use them to perform a downstream task.…
Sarcasm is a linguistic expression often used to communicate the opposite of what is said, usually something that is very unpleasant with an intention to insult or ridicule. Inherent ambiguity in sarcastic expressions, make sarcasm…