Persona-Model Collapse in Emergent Misalignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Costa, Davi Bastos, Vicente, Renato
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
by: Betley, Jan, et al.
Published: (2025)

Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
by: Panpatil, Siddhant, et al.
Published: (2025)

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
by: Hu, Xuhao, et al.
Published: (2025)

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
by: Shayegani, Erfan, et al.
Published: (2025)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
by: Wang, Chunxiao
Published: (2026)

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
by: Boreiko, Valentyn, et al.
Published: (2024)

DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded Aggregation
by: Segal, Tom, et al.
Published: (2024)

Personal Information Parroting in Language Models
by: Subramani, Nishant, et al.
Published: (2026)

Watermarking Makes Language Models Radioactive
by: Sander, Tom, et al.
Published: (2024)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Instructional Fingerprinting of Large Language Models
by: Xu, Jiashu, et al.
Published: (2024)

Rethinking How to Evaluate Language Model Jailbreak
by: Cai, Hongyu, et al.
Published: (2024)

Large Language Models in Cybersecurity: State-of-the-Art
by: Motlagh, Farzad Nourmohammadzadeh, et al.
Published: (2024)

Duwak: Dual Watermarks in Large Language Models
by: Zhu, Chaoyi, et al.
Published: (2024)

Jailbreaking Large Language Models with Symbolic Mathematics
by: Bethany, Emet, et al.
Published: (2024)

Learnable Privacy Neurons Localization in Language Models
by: Chen, Ruizhe, et al.
Published: (2024)

On Adversarial Robustness of Language Models in Transfer Learning
by: Turbal, Bohdan, et al.
Published: (2024)

Directional Embedding Smoothing for Robust Vision Language Models
by: Wang, Ye, et al.
Published: (2026)

The Resurgence of GCG Adversarial Attacks on Large Language Models
by: Tan, Yuting, et al.
Published: (2025)

Machine Unlearning of Pre-trained Large Language Models
by: Yao, Jin, et al.
Published: (2024)

Was it Slander? Towards Exact Inversion of Generative Language Models
by: Skapars, Adrians, et al.
Published: (2024)

On the Role of Attention Heads in Large Language Model Safety
by: Zhou, Zhenhong, et al.
Published: (2024)

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

Interpreting the Repeated Token Phenomenon in Large Language Models
by: Yona, Itay, et al.
Published: (2025)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

FIT to Forget: Robust Continual Unlearning for Large Language Models
by: Xu, Xiaoyu, et al.
Published: (2026)

A Study of Backdoors in Instruction Fine-tuned Language Models
by: Raghuram, Jayaram, et al.
Published: (2024)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
by: Wang, Zhepeng, et al.
Published: (2024)

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting
by: Liu, Fuqiang, et al.
Published: (2024)

Improving Your Model Ranking on Chatbot Arena by Vote Rigging
by: Min, Rui, et al.
Published: (2025)

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
by: Xu, Xiaoyu, et al.
Published: (2025)

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

Evading Data Contamination Detection for Language Models is (too) Easy
by: Dekoninck, Jasper, et al.
Published: (2024)

Extracting Training Data from Diffusion Language Models via Infilling
by: Wang, Yihan, et al.
Published: (2026)

Time Travel in LLMs: Tracing Data Contamination in Large Language Models
by: Golchin, Shahriar, et al.
Published: (2023)

Detecting Training Data of Large Language Models via Expectation Maximization
by: Kim, Gyuwan, et al.
Published: (2024)

SVIP: Towards Verifiable Inference of Open-source Large Language Models
by: Sun, Yifan, et al.
Published: (2024)

PostMark: A Robust Blackbox Watermark for Large Language Models
by: Chang, Yapei, et al.
Published: (2024)

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
by: Wei, Zeming, et al.
Published: (2023)