Cover Image

Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Le, Zhao, Zhengyue, Zheng, Yawen, Liu, Yunhao
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
by: Kopiczko, Dawid J., et al.
Published: (2026)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
by: Le, Chenqian, et al.
Published: (2025)

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
by: Puerto, Haritz, et al.
Published: (2024)

Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales
by: Yan, Jianzhi, et al.
Published: (2025)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
by: Ma, Xinyin, et al.
Published: (2025)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
by: Du, Yanrui, et al.
Published: (2026)

AS-ES Learning: Towards Efficient CoT Learning in Small Models
by: Xi, Nuwa, et al.
Published: (2024)

Generating Effective CoT Traces for Mitigating Causal Hallucination
by: Zhao, Yiheng, et al.
Published: (2026)

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
by: Yang, Cehao, et al.
Published: (2025)

CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers
by: Le, Anh Duc, et al.
Published: (2025)

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
by: Tong, Zhao, et al.
Published: (2026)

Efficient Long CoT Reasoning in Small Language Models
by: Wang, Zhaoyang, et al.
Published: (2025)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
by: Deng, Yuntian, et al.
Published: (2024)

DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment
by: Zhu, Liang, et al.
Published: (2026)

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

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
by: Sprague, Zayne, et al.
Published: (2024)

Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
by: Hu, Tianxiang, et al.
Published: (2024)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
by: Jin, Senjie, et al.
Published: (2025)

ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection
by: Delaval, Axel, et al.
Published: (2025)

D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
by: Zhou, Weibo, et al.
Published: (2025)

Fine-Tuning Language Models Using Formal Methods Feedback
by: Yang, Yunhao, et al.
Published: (2023)

Investigating CoT Monitorability in Large Reasoning Models
by: Yang, Shu, et al.
Published: (2025)

Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity
by: Ren, Xuan, et al.
Published: (2025)

Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
by: Kumar, Adarsh, et al.
Published: (2025)

The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning
by: Zheng, Tianshi, et al.
Published: (2025)

Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning
by: Chien, Chung-Ming, et al.
Published: (2024)

Investigating Mysteries of CoT-Augmented Distillation
by: Wadhwa, Somin, et al.
Published: (2024)

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
by: Liu, Tengxuan, et al.
Published: (2025)

GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
by: Fang, Zhouxiang, et al.
Published: (2026)

Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
by: Zheng, Xin, et al.
Published: (2024)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
by: Yan, Shaotian, et al.
Published: (2026)

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step
by: Wang, Zezhong, et al.
Published: (2024)

Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
by: Wang, Ru, et al.
Published: (2025)

ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
by: Liu, Yanming, et al.
Published: (2024)

SIM-CoT: Supervised Implicit Chain-of-Thought
by: Wei, Xilin, et al.
Published: (2025)

CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
by: Yu, Ping, et al.
Published: (2025)

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis
by: Zhang, Bohan, et al.
Published: (2025)

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
by: Zhao, Hao, et al.
Published: (2024)

Dialect Identification Using Resource-Efficient Fine-Tuning Approaches
by: Lin, Zirui, et al.
Published: (2025)

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