Imagen de Portada

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Yang, Sheng, Qiang, Yang, Yehan, Zhang, Xueyao, Cao, Juan
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning
por: Shi, Yuhui, et al.
Publicado: (2025)

PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
por: Li, Jing-Jing, et al.
Publicado: (2026)

LLM-based Semantic Augmentation for Harmful Content Detection
por: Meguellati, Elyas, et al.
Publicado: (2025)

Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
por: Zhang, Chi, et al.
Publicado: (2025)

LLM-Generated Fake News Induces Truth Decay in News Ecosystem: A Case Study on Neural News Recommendation
por: Hu, Beizhe, et al.
Publicado: (2025)

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection
por: Li, Yang, et al.
Publicado: (2026)

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas
por: Wu, Ya, et al.
Publicado: (2025)

Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting
por: Nan, Qiong, et al.
Publicado: (2023)

The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation
por: Zhou, Yuhang, et al.
Publicado: (2025)

Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
por: Harvey, Emma, et al.
Publicado: (2025)

Longitudinal Monitoring of LLM Content Moderation of Social Issues
por: Dai, Yunlang, et al.
Publicado: (2025)

Harmful Suicide Content Detection
por: Park, Kyumin, et al.
Publicado: (2024)

GLARE: Agentic Reasoning for Legal Judgment Prediction
por: Yang, Xinyu, et al.
Publicado: (2025)

Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework
por: Gajewska, Ewelina, et al.
Publicado: (2026)

Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
por: Hu, Beizhe, et al.
Publicado: (2023)

Taxonomizing Representational Harms using Speech Act Theory
por: Corvi, Emily, et al.
Publicado: (2025)

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
por: Chehbouni, Khaoula, et al.
Publicado: (2024)

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
por: Jain, Shomik, et al.
Publicado: (2025)

AppellateGen: A Benchmark for Appellate Legal Judgment Generation
por: Yang, Hongkun, et al.
Publicado: (2026)

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection
por: Sen, Indira, et al.
Publicado: (2023)

From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents
por: Yu, Jifan, et al.
Publicado: (2024)

Between Rules and Reality: On the Context Sensitivity of LLM Moral Judgment
por: Sauter, Adrian, et al.
Publicado: (2026)

Careless Whisper: Speech-to-Text Hallucination Harms
por: Koenecke, Allison, et al.
Publicado: (2024)

Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction
por: Liu, Junkai, et al.
Publicado: (2024)

JurisCTC: Enhancing Legal Judgment Prediction via Cross-Domain Transfer and Contrastive Learning
por: Kang, Zhaolu, et al.
Publicado: (2025)

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
por: Mi, Hao, et al.
Publicado: (2026)

Disentangling Learning from Judgment: Representation Learning for Open Response Analytics
por: Borchers, Conrad, et al.
Publicado: (2025)

Language of Thought Shapes Output Diversity in Large Language Models
por: Xu, Shaoyang, et al.
Publicado: (2026)

Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models
por: Nan, Qiong, et al.
Publicado: (2024)

Exploring news intent and its application: A theory-driven approach
por: Wang, Zhengjia, et al.
Publicado: (2023)

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs
por: Ghorbanpour, Faeze, et al.
Publicado: (2025)

Multilingualism, Transnationality, and K-pop in the Online #StopAsianHate Movement
por: Masis, Tessa, et al.
Publicado: (2025)

A Capabilities Approach to Studying Bias and Harm in Language Technologies
por: Nigatu, Hellina Hailu, et al.
Publicado: (2024)

Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
por: Cai, Yunna, et al.
Publicado: (2025)

Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
por: Arnaiz-Rodriguez, Adrian, et al.
Publicado: (2025)

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?
por: Cyberey, Hannah, et al.
Publicado: (2024)

SESGO: Spanish Evaluation of Stereotypical Generative Outputs
por: Robles, Melissa, et al.
Publicado: (2025)

Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
por: Dorn, Rebecca, et al.
Publicado: (2024)

Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once
por: Dhingra, Harnoor
Publicado: (2026)

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
por: Yuan, Yuan, et al.
Publicado: (2025)