Imagen de Portada

Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Selvanayagam, Niruthiha, Kurti, Ted
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multidimensional Analysis of Specific Language Impairment Using Unsupervised Learning Through PCA and Clustering
por: Selvanayagam, Niruthiha
Publicado: (2025)

Advancing Hate Speech Detection with Transformers: Insights from the MetaHate
por: Chapagain, Santosh, et al.
Publicado: (2025)

HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models
por: Sen, Tanmay, et al.
Publicado: (2024)

Self-Admitted Technical Debt in LLM Software: An Empirical Comparison with ML and Non-ML Software
por: Selvanayagam, Niruthiha, et al.
Publicado: (2026)

Hate Speech Detection with Generalizable Target-aware Fairness
por: Chen, Tong, et al.
Publicado: (2024)

Understanding Unimodal Bias in Multimodal Deep Linear Networks
por: Zhang, Yedi, et al.
Publicado: (2023)

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns
por: Shen, Xinyue, et al.
Publicado: (2025)

Hate Speech Detection and Classification in Amharic Text with Deep Learning
por: Gashe, Samuel Minale, et al.
Publicado: (2024)

An Effective, Robust and Fairness-aware Hate Speech Detection Framework
por: Mou, Guanyi, et al.
Publicado: (2024)

Attentive Fusion: A Transformer-based Approach to Multimodal Hate Speech Detection
por: Mandal, Atanu, et al.
Publicado: (2024)

Generative AI Takes a Statistics Exam: A Comparison of Performance between ChatGPT3.5, ChatGPT4, and ChatGPT4o-mini
por: McGee, Monnie, et al.
Publicado: (2025)

UNITE-FND: Reframing Multimodal Fake News Detection through Unimodal Scene Translation
por: Mukherjee, Arka, et al.
Publicado: (2025)

Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition
por: Huang, Chengxiang, et al.
Publicado: (2025)

Rebalanced Multimodal Learning with Data-aware Unimodal Sampling
por: Jiang, Qingyuan, et al.
Publicado: (2025)

Unimodal and Multimodal Sensor Fusion for Wearable Activity Recognition
por: Bello, Hymalai
Publicado: (2024)

Towards Generalizable Generic Harmful Speech Datasets for Implicit Hate Speech Detection
por: Almohaimeed, Saad, et al.
Publicado: (2025)

Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection
por: Eilertsen, Brage, et al.
Publicado: (2025)

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
por: Sheth, Paras, et al.
Publicado: (2024)

Multimodal Representation Learning by Alternating Unimodal Adaptation
por: Zhang, Xiaohui, et al.
Publicado: (2023)

Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion
por: Li, Jiagen, et al.
Publicado: (2025)

On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
por: Karchmer, Ari
Publicado: (2024)

A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages
por: Das, Susmita, et al.
Publicado: (2024)

Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition
por: Labadie-Tamayo, Roberto, et al.
Publicado: (2025)

BOISHOMMO: Holistic Approach for Bangla Hate Speech
por: Kafi, Md Abdullah Al, et al.
Publicado: (2025)

Causality Guided Representation Learning for Cross-Style Hate Speech Detection
por: Zhao, Chengshuai, et al.
Publicado: (2025)

Investigating Annotator Bias in Large Language Models for Hate Speech Detection
por: Das, Amit, et al.
Publicado: (2024)

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
por: Stepanov, Ihor, et al.
Publicado: (2026)

MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels
por: Xu, Lilin, et al.
Publicado: (2024)

Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis
por: Mai, Sijie, et al.
Publicado: (2024)

Dynamic Optimization and Safety Indicator Injection for Jailbreaking Text-to-Image Models with Multimodal Safety Filters
por: Chen, Zixuan, et al.
Publicado: (2025)

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
por: Wang, Yihua, et al.
Publicado: (2025)

ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos
por: Rehman, Mohammad Zia Ur, et al.
Publicado: (2025)

Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks
por: Azumah, Sylvia Worlali, et al.
Publicado: (2024)

Transformers and Ensemble methods: A solution for Hate Speech Detection in Arabic languages
por: de Paula, Angel Felipe Magnossão, et al.
Publicado: (2023)

On Importance of Code-Mixed Embeddings for Hate Speech Identification
por: Jagdale, Shruti, et al.
Publicado: (2024)

Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference
por: Oshima, Yuta, et al.
Publicado: (2024)

SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection
por: Mou, Guanyi, et al.
Publicado: (2024)

Unimodal Strategies in Density-Based Clustering
por: Nir, Oron, et al.
Publicado: (2025)

Aligning Multimodal Representations through an Information Bottleneck
por: Almudévar, Antonio, et al.
Publicado: (2025)

Learning Optimal Multimodal Information Bottleneck Representations
por: Wu, Qilong, et al.
Publicado: (2025)