Cover Image

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Giordani, Jeremiah
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
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)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
by: Pan, Birong, et al.
Published: (2025)

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

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
by: Hahm, Dongyoon, et al.
Published: (2025)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
by: Soligo, Anna, et al.
Published: (2026)

Teaching LLMs How to Learn with Contextual Fine-Tuning
by: Choi, Younwoo, et al.
Published: (2025)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

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

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
by: Li, Guanlin, et al.
Published: (2025)

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

Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
by: Gulati, Idhant, et al.
Published: (2026)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
by: Mushtaq, Erum, et al.
Published: (2025)

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

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
by: Hahm, Dongyoon, et al.
Published: (2026)

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
by: Shen, Qian, et al.
Published: (2026)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
by: Sahoo, Subramanyam
Published: (2026)

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
by: Ovadia, Oded, et al.
Published: (2023)

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
by: Mishra, Aayush, et al.
Published: (2025)

Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
by: Ponkshe, Kaustubh, et al.
Published: (2025)

EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMs
by: Guo, Song, et al.
Published: (2024)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
by: Wang, Xu, et al.
Published: (2025)

Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data
by: Rallapalli, Swati, et al.
Published: (2025)

Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
by: Khadangi, Afshin, et al.
Published: (2025)

Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models
by: Arteaga, Gabriel Y., et al.
Published: (2024)

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
by: Jan, Essa, et al.
Published: (2024)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
by: Asif, Sadia, et al.
Published: (2026)

LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs
by: Kim, Taeho, et al.
Published: (2024)

ALKAFI-LLAMA3: Fine-Tuning LLMs for Precise Legal Understanding in Palestine
by: Qasem, Rabee, et al.
Published: (2024)

Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
by: Thulke, David, et al.
Published: (2024)

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

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
by: Ling, Zhenqing, et al.
Published: (2025)

Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
by: Wang, Tuowei, et al.
Published: (2025)

LLMs Meet Finance: Fine-Tuning Foundation Models for the Open FinLLM Leaderboard
by: Rao, Varun, et al.
Published: (2025)

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs
by: Wang, Zige, et al.
Published: (2025)

Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
by: Wang, Ruoyu, et al.
Published: (2024)

Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs
by: Zhang, Zheng, et al.
Published: (2024)

Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
by: Kang, Feiyang, et al.
Published: (2024)

Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
by: Chan, Yik Siu, et al.
Published: (2025)

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
by: Meng, Haoming, et al.
Published: (2026)

Test-Time Safety Alignment
by: Saglam, Baturay, et al.
Published: (2026)