Cover Image

Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vaugrante, Laurène, Weckauff, Anietta, Hagendorff, Thilo
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions
by: Vaugrante, Laurène, et al.
Published: (2024)

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

Deception Abilities Emerged in Large Language Models
by: Hagendorff, Thilo
Published: (2023)

Characterizing the Consistency of the Emergent Misalignment Persona
by: Weckauff, Anietta, et al.
Published: (2026)

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models
by: Hagendorff, Thilo
Published: (2025)

Evaluation Awareness in Language Models Has Limited Effect on Behaviour
by: Knecht, Amelie, et al.
Published: (2026)

Decoding-time Realignment of Language Models
by: Liu, Tianlin, et al.
Published: (2024)

Beyond Chains of Thought: Benchmarking Latent-Space Reasoning Abilities in Large Language Models
by: Hagendorff, Thilo, et al.
Published: (2025)

"Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior
by: Lulla, Roshni, et al.
Published: (2026)

Persona-Model Collapse in Emergent Misalignment
by: Costa, Davi Bastos, et al.
Published: (2026)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
by: Chua, James, et al.
Published: (2025)

Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms
by: Meding, Kristof, et al.
Published: (2023)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
by: Askin, Baris, et al.
Published: (2026)

PRIDE -- Parameter-Efficient Reduction of Identity Discrimination for Equality in LLMs
by: Menke, Maluna, et al.
Published: (2025)

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
by: Li, Yue, et al.
Published: (2025)

The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs
by: Dickson, Craig
Published: (2025)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

CALM: Culturally Self-Aware Language Models
by: Shen, Lingzhi, et al.
Published: (2026)

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

Emergent Abilities in Reduced-Scale Generative Language Models
by: Muckatira, Sherin, et al.
Published: (2024)

Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models
by: Jotautaitė, Monika, et al.
Published: (2025)

Emergent Stack Representations in Modeling Counter Languages Using Transformers
by: Tiwari, Utkarsh, et al.
Published: (2025)

Domain-Shift-Aware Conformal Prediction for Large Language Models
by: Lin, Zhexiao, et al.
Published: (2025)

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
by: Karvonen, Adam
Published: (2024)

Do Large Language Models Show Biases in Causal Learning?
by: Carro, Maria Victoria, et al.
Published: (2024)

Large Reasoning Models Are Autonomous Jailbreak Agents
by: Hagendorff, Thilo, et al.
Published: (2025)

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
by: Wu, Xuansheng, et al.
Published: (2023)

Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs
by: Bozoukov, Matthew, et al.
Published: (2025)

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
by: Zhang, Yanan, et al.
Published: (2024)

Emergent Semantic Role Understanding in Language Models
by: Griffiths, Carla, et al.
Published: (2026)

Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study
by: Li, Yufei, et al.
Published: (2024)

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
by: Sawmya, Shashata, et al.
Published: (2025)

Emergent Representations of Program Semantics in Language Models Trained on Programs
by: Jin, Charles, et al.
Published: (2023)

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models
by: Ballout, Mohamad, et al.
Published: (2024)

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
by: Tamoyan, Hovhannes, et al.
Published: (2025)

Emergent Abilities in Large Language Models: A Survey
by: Berti, Leonardo, et al.
Published: (2025)

Epistemic Traps: Rational Misalignment Driven by Model Misspecification
by: Xu, Xingcheng, et al.
Published: (2026)

Continual Learning Under Language Shift
by: Gogoulou, Evangelia, et al.
Published: (2023)

Does Visual Rendering Bypass Tokenization? Investigating Script-Tokenizer Misalignment in Pixel-Based Language Models
by: Susanto, Lucky, et al.
Published: (2026)

Cascade-Aware Training of Language Models
by: Wang, Congchao, et al.
Published: (2024)