Target Span Detection for Implicit Harmful Content
Identifying the targets of hate speech is a crucial step in grasping the nature of such speech and, ultimately, in improving the detection of offensive posts on online forums. Much harmful content on online platforms uses implicit language especially when targeting vulnerable and protected groups such as using stereotypical characteristics instead of explicit target names, making it harder to detect and mitigate the language. In this study, we focus on identifying implied targets of hate speech, essential for recognizing subtler hate speech and enhancing the detection of harmful content on digital platforms. We define a new task aimed at identifying the targets even when they are not explicitly stated. To address that task, we collect and annotate target spans in three prominent implicit hate speech datasets: SBIC, DynaHate, and IHC. We call the resulting merged collection Implicit-Target-Span. The collection is achieved using an innovative pooling method with matching scores based on human annotations and Large Language Models (LLMs). Our experiments indicate that Implicit-Target-Span provides a challenging test bed for target span detection methods.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the overall efficiency and accuracy of content…
Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to convey harmful opinions through subtle rhetorical devices like irony and metaphor. Existing detection approaches, includ…
KID: Knowledge-Injected Dual-Head Learning for Knowledge-Grounded Harmful Meme Detection
Internet memes have become pervasive carriers of digital culture on social platforms. However, their heavy reliance on metaphors and sociocultural context also makes them subtle vehicles for harmful content, posing signi…
Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection m…
Bias DetectionA Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. B…
Prompt Engineering