Imagen de Portada

Fake Alignment: Are LLMs Really Aligned Well?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yixu, Teng, Yan, Huang, Kexin, Lyu, Chengqi, Zhang, Songyang, Zhang, Wenwei, Ma, Xingjun, Jiang, Yu-Gang, Qiao, Yu, Wang, Yingchun
Formato:	Preprint
Publicado:	2023
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Towards Context-Invariant Safety Alignment for Large Language Models
por: Wang, Yixu, et al.
Publicado: (2026)

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
por: Yu, Jiaqi, et al.
Publicado: (2026)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
por: Chen, Yunhao, et al.
Publicado: (2025)

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
por: Gu, Yuzhe, et al.
Publicado: (2025)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
por: Wang, Yixu, et al.
Publicado: (2025)

Flames: Benchmarking Value Alignment of LLMs in Chinese
por: Huang, Kexin, et al.
Publicado: (2023)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
por: Wang, Yixu, et al.
Publicado: (2025)

HoneypotNet: Backdoor Attacks Against Model Extraction
por: Wang, Yixu, et al.
Publicado: (2025)

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
por: Liu, Shudong, et al.
Publicado: (2025)

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
por: Gu, Tianle, et al.
Publicado: (2024)

The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner
por: Hua, Zhouqi, et al.
Publicado: (2025)

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
por: Song, Jiaxin, et al.
Publicado: (2025)

IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
por: Wang, Ruofan, et al.
Publicado: (2024)

Are Your LLMs Capable of Stable Reasoning?
por: Liu, Junnan, et al.
Publicado: (2024)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
por: Gu, Tianle, et al.
Publicado: (2025)

EnJa: Ensemble Jailbreak on Large Language Models
por: Zhang, Jiahao, et al.
Publicado: (2024)

ANAH: Analytical Annotation of Hallucinations in Large Language Models
por: Ji, Ziwei, et al.
Publicado: (2024)

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
por: Gu, Yuzhe, et al.
Publicado: (2024)

A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
por: Yao, Yang, et al.
Publicado: (2025)

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models
por: Zhao, Haiquan, et al.
Publicado: (2024)

Mechanistic Origin of Moral Indifference in Language Models
por: Li, Lingyu, et al.
Publicado: (2026)

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark
por: Liu, Hongwei, et al.
Publicado: (2024)

MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
por: Gu, Tianle, et al.
Publicado: (2024)

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models
por: Wang, Zilong, et al.
Publicado: (2025)

AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
por: Wang, Yixu, et al.
Publicado: (2025)

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
por: Lyu, Chengqi, et al.
Publicado: (2025)

CIBench: Evaluating Your LLMs with a Code Interpreter Plugin
por: Zhang, Chuyu, et al.
Publicado: (2024)

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
por: Gao, Songyang, et al.
Publicado: (2024)

MESA: Improving MoE Safety Alignment via Decentralized Expertise
por: Sun, Yitong, et al.
Publicado: (2026)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
por: Zhao, Yunhan, et al.
Publicado: (2026)

Do LLMs Really Think Step-by-step In Implicit Reasoning?
por: Yu, Yijiong
Publicado: (2024)

Does Alignment Tuning Really Break LLMs' Internal Confidence?
por: Oh, Hongseok, et al.
Publicado: (2024)

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
por: Clymer, Joshua, et al.
Publicado: (2024)

Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
por: Yao, Yang, et al.
Publicado: (2025)

AlignSurvey: A Comprehensive Benchmark for Human Preferences Alignment in Social Surveys
por: Lin, Chenxi, et al.
Publicado: (2025)

Rethinking Verification for LLM Code Generation: From Generation to Testing
por: Ma, Zihan, et al.
Publicado: (2025)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
por: Li, Teng, et al.
Publicado: (2025)

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
por: Wang, Xin, et al.
Publicado: (2025)

Training Language Models to Critique With Multi-agent Feedback
por: Lan, Tian, et al.
Publicado: (2024)

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
por: Song, Zifan, et al.
Publicado: (2024)