Imagen de Portada

Toxicity Detection for Free

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hu, Zhanhao, Piet, Julien, Zhao, Geng, Jiao, Jiantao, Wagner, David
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generative AI Security: Challenges and Countermeasures
por: Zhu, Banghua, et al.
Publicado: (2024)

Mark My Words: Analyzing and Evaluating Language Model Watermarks
por: Piet, Julien, et al.
Publicado: (2023)

$k$NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
por: Wong, Kahim, et al.
Publicado: (2026)

GradShield: Alignment Preserving Finetuning
por: Hu, Zhanhao, et al.
Publicado: (2026)

Toward a Theory of Tokenization in LLMs
por: Rajaraman, Nived, et al.
Publicado: (2024)

Efficient Prompt Caching via Embedding Similarity
por: Zhu, Hanlin, et al.
Publicado: (2024)

Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
por: Zhao, Yibo, et al.
Publicado: (2024)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
por: Piet, Julien, et al.
Publicado: (2023)

Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
por: Zhu, Banghua, et al.
Publicado: (2024)

Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety
por: Korotkova, Elizaveta, et al.
Publicado: (2023)

Parser-Free Querying of Security Logs
por: Luo, Evan, et al.
Publicado: (2026)

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
por: Piet, Julien, et al.
Publicado: (2025)

Culture Matters in Toxic Language Detection in Persian
por: Bokaei, Zahra, et al.
Publicado: (2025)

Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification
por: Bell, Samuel J., et al.
Publicado: (2025)

Web Agents Should Adopt the Plan-Then-Execute Paradigm
por: Piet, Julien, et al.
Publicado: (2026)

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
por: Yang, Shujian, et al.
Publicado: (2025)

Concept-Based Interpretability for Toxicity Detection
por: Garg, Samarth, et al.
Publicado: (2025)

In-game Toxic Language Detection: Shared Task and Attention Residuals
por: Jia, Yuanzhe, et al.
Publicado: (2022)

Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling
por: Atil, Berk, et al.
Publicado: (2026)

Detecting Toxic Language: Ontology and BERT-based Approaches for Bulgarian Text
por: Berbatova, Melania, et al.
Publicado: (2026)

Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech
por: Gupta, Soumyajit, et al.
Publicado: (2022)

ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection
por: Li, Boyang, et al.
Publicado: (2026)

Thinking LLMs: General Instruction Following with Thought Generation
por: Wu, Tianhao, et al.
Publicado: (2024)

ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
por: Hoang, Nhat M., et al.
Publicado: (2024)

ViToSA: Audio-Based Toxic Spans Detection on Vietnamese Speech Utterances
por: Do, Huy Ba, et al.
Publicado: (2025)

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
por: Muminovic, Amel, et al.
Publicado: (2025)

Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
por: Faisal, Fahim, et al.
Publicado: (2024)

Toxicity Classification in Ukrainian
por: Dementieva, Daryna, et al.
Publicado: (2024)

Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset
por: Luo, Man, et al.
Publicado: (2025)

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
por: Zhu, Hanlin, et al.
Publicado: (2024)

Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities
por: Pandiani, Delfina Sol Martinez, et al.
Publicado: (2024)

PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
por: Jain, Devansh, et al.
Publicado: (2024)

FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts
por: Brun, Caroline, et al.
Publicado: (2024)

Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata
por: Schurger-Foy, Adrien, et al.
Publicado: (2025)

On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection
por: Elsafoury, Fatma, et al.
Publicado: (2023)

EmbedLLM: Learning Compact Representations of Large Language Models
por: Zhuang, Richard, et al.
Publicado: (2024)

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
por: Hu, Yujia, et al.
Publicado: (2025)

Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media
por: Assenmacher, Dennis, et al.
Publicado: (2025)

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
por: Duan, Zenghao, et al.
Publicado: (2025)

Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
por: Uppaal, Rheeya, et al.
Publicado: (2024)