conftrace_

harmful content detection

54 papers

Explore in graph

Also known as

HCD

Co-occurring keywords

large language model (13587) content moderation (201) text classification (6793) multimodal learning (4645) ai safety (235) harmful content (66) hate speech detection (723) safety evaluation (94) social media analysis (699) multi-agent system (1819)

Papers

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs AAAI 2026
Failures to Surface Harmful Contents in Video Large Language Models AAAI 2026
Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation ACL 2026
BigTokDetect: A Clinically-Informed Vision–Language Modeling Framework for Detecting Pro-Bigorexia Videos on TikTok EACL 2026
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects ACL 2026
LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety EMNLP 2025
Conspiracy Theories and Where to Find Them on TikTok ACL 2025
Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025
NLP-ADBench: NLP Anomaly Detection Benchmark EMNLP 2025
AraSafe: Benchmarking Safety in Arabic LLMs EMNLP 2025
AI Tools Can Generate Misculture Visuals! Detecting Prompts Generating Misculture Visuals For Prevention ACL 2025
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance EMNLP 2025
MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025
SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025
ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content EMNLP 2025
Leveraging Large Language Models in Detecting Anti-LGBTQIA+ User-generated Texts NAACL 2025
CALM: Curiosity-Driven Auditing for Large Language Models AAAI 2025
Rainbow-Teaming for the Polish Language: A Reproducibility Study NAACL 2025
MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection ACL 2025
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025
ContextAware: A Multi-Agent Framework for Detecting Harmful Image-Based Comments on Social Media IJCAI 2025
Granite Guardian: Comprehensive LLM Safeguarding NAACL 2025
Fine-Grained Transfer Learning for Harmful Content Detection through Label-Specific Soft Prompt Tuning NAACL 2025
Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts ACL 2025