# Target Span Detection for Implicit Harmful Content

arXiv: https://arxiv.org/abs/2403.19836 · HTML: https://mlsanity.com/paper/2403.19836/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting](https://mlsanity.com/paper/2004.14088/) (2020)
- [Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go](https://mlsanity.com/paper/2103.00153/) (2021)
- [Explainable Abuse Detection as Intent Classification and Slot Filling](https://mlsanity.com/paper/2210.02659/) (2022)
- [Towards Ethics by Design in Online Abusive Content Detection](https://mlsanity.com/paper/2010.14952/) (2020)

## Built on by (most cited first, 8 of 8)

- [AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection](https://mlsanity.com/paper/2505.19528/) (2025)
- [Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon](https://mlsanity.com/paper/2505.22184/) (2025)
- [Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text](https://mlsanity.com/paper/2510.03683/) (2025)
- [More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection](https://mlsanity.com/paper/2603.21298/) (2026)
- [ToxiREX: A Dataset on Toxic REasoning in ConteXt](https://mlsanity.com/paper/2606.27981/) (2026)
- [AEGIS: Awareness-Enhanced Guidance for Iterative Safeguard](https://mlsanity.com/paper/2607.17713/) (2026)
- [HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models](https://mlsanity.com/paper/2607.21105/) (2026)
- [Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech](https://mlsanity.com/paper/2608.27462/) (2026)

## Abstract (arXiv)

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.