:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Zhaoxin, Chen, Borui, Hu, Yiming, Qu, Youyang, Zhu, Tianqing, Gao, Longxiang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	https://arxiv.org/abs/2511.21718
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
por: Qu, Youyang, et al.
Publicado: (2024)

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
por: Tan, Chenchen, et al.
Publicado: (2025)

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
por: Tan, Chenchen, et al.
Publicado: (2026)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
por: Xing, Wenpeng, et al.
Publicado: (2025)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
por: Wang, Linlin, et al.
Publicado: (2025)

When Safety Fails Before the Answer: Benchmarking Harmful Behavior Detection in Reasoning Chains
por: Kakkar, Ishita, et al.
Publicado: (2026)

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
por: Chehbouni, Khaoula, et al.
Publicado: (2024)

Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
por: He, Mutian, et al.
Publicado: (2022)

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking
por: Li, Jingru, et al.
Publicado: (2026)

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

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
por: Qu, Jiaming, et al.
Publicado: (2026)

Dishonesty in Helpful and Harmless Alignment
por: Huang, Youcheng, et al.
Publicado: (2024)

ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
por: Zhang, Liyu, et al.
Publicado: (2024)

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
por: Zhang, Xiaoyun, et al.
Publicado: (2024)

From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding
por: Cai, Borui, et al.
Publicado: (2023)

"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
por: Dammu, Preetam Prabhu Srikar, et al.
Publicado: (2024)

Should LLM Safety Be More Than Refusing Harmful Instructions?
por: Maskey, Utsav, et al.
Publicado: (2025)

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
por: Kong, Jiawei, et al.
Publicado: (2025)

Owner-Harm: A Missing Threat Model for AI Agent Safety
por: Zhang, Dongcheng, et al.
Publicado: (2026)

Causal Fingerprints of AI Generative Models
por: Xu, Hui, et al.
Publicado: (2025)

Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
por: Chu, Junjie, et al.
Publicado: (2026)

Beyond Words: Multimodal LLM Knows When to Speak
por: Liao, Zikai, et al.
Publicado: (2025)

LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
por: Vishnubhotla, Krishnapriya, et al.
Publicado: (2026)

Compromising Honesty and Harmlessness in Language Models via Deception Attacks
por: Vaugrante, Laurène, et al.
Publicado: (2025)

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
por: Wang, Shang, et al.
Publicado: (2024)

FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity
por: Cui, Shiyao, et al.
Publicado: (2023)

When Wording Steers the Evaluation: Framing Bias in LLM judges
por: Hwang, Yerin, et al.
Publicado: (2026)

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

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
por: Yang, Langqi, et al.
Publicado: (2025)

HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate
por: Zhu, Shenzhe
Publicado: (2025)

Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF
por: Zheng, Chen, et al.
Publicado: (2024)

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention
por: Feng, Zhaoxin, et al.
Publicado: (2025)

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios
por: Gao, Yuan, et al.
Publicado: (2025)

Reinforcement Learning Amplifies Emergent Misalignment from Harmless Rewards
por: Jørgenvåg, Magnus, et al.
Publicado: (2026)

Too Helpful, Too Harmless, Too Honest or Just Right?
por: Kashyap, Gautam Siddharth, et al.
Publicado: (2025)

Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture
por: Zhang, Longxiang, et al.
Publicado: (2026)

Towards Harmless Multimodal Assistants with Blind Preference Optimization
por: Li, Yongqi, et al.
Publicado: (2025)

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
por: Yang, Jinluan, et al.
Publicado: (2025)

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
por: Wang, Pengyu, et al.
Publicado: (2024)

They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References
por: Tripathi, Sahil, et al.
Publicado: (2026)