From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation

arXiv:2608.25605 · cs.CL · Submitted 2026-08-26 · Read on arXiv

cs.CL

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/TUM-NLP/HIPPO

Project page: https://hasocfire.github.io/hasoc/2019/call_for_participation.html

Terminology

• Benchmark — 9× in this paper · explained in 2 episodes
• Generalization — 9× in this paper · explained in 13 episodes
• Instruction Tuning — 8× in this paper · explained in 2 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• F1 Score — 3× in this paper · explained in 3 episodes
• Civil Comments — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Workshop on Online Abuse and Harms — 2× in this paper
• Adaptability — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Ensemble Learning — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Hierarchical Framework — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Phi-4 Technical Report
• Automated Detection of Cyberbullying Against Women and Immigrants and Cross-domain Adaptability
• No Language Left Behind: Scaling Human-Centered Machine Translation
• Hate Speech Dataset from a White Supremacy Forum
• The Llama 3 Herd of Models
• Right-wing German Hate Speech on Twitter: Analysis and Automatic Detection
• Investigating Data Contamination for Pre-training Language Models
• Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning
• Detecting Online Hate Speech Using Context Aware Models
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Multilingual and Multi-Aspect Hate Speech Analysis
• Toxicity Detection: Does Context Really Matter?
• A Benchmark Dataset for Learning to Intervene in Online Hate Speech
• Qwen3 Technical Report
• HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
• Predicting the Type and Target of Offensive Posts in Social Media

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering