Cover Image

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mao, Yingzhi, Zhang, Chunkang, Wang, Junxiang, Guan, Xinyan, Cao, Boxi, Lu, Yaojie, Lin, Hongyu, Han, Xianpei, Sun, Le
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
by: Yan, Xinru, et al.
Published: (2026)

The Life Cycle of Knowledge in Big Language Models: A Survey
by: Cao, Boxi, et al.
Published: (2023)

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
by: Zheng, Jiasheng, et al.
Published: (2024)

REInstruct: Building Instruction Data from Unlabeled Corpus
by: Chen, Shu, et al.
Published: (2024)

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
by: Guan, Xinyan, et al.
Published: (2024)

Multi-Facet Counterfactual Learning for Content Quality Evaluation
by: Zheng, Jiasheng, et al.
Published: (2024)

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
by: Guan, Xinyan, et al.
Published: (2025)

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
by: Zheng, Jiasheng, et al.
Published: (2026)

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
by: Wen, Xueru, et al.
Published: (2024)

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
by: Liu, Yanjiang, et al.
Published: (2025)

Executing Natural Language-Described Algorithms with Large Language Models: An Investigation
by: Zheng, Xin, et al.
Published: (2024)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
by: Ma, Zhengzhao, et al.
Published: (2026)

Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?
by: Bian, Ning, et al.
Published: (2024)

Meta-Cognitive Analysis: Evaluating Declarative and Procedural Knowledge in Datasets and Large Language Models
by: Li, Zhuoqun, et al.
Published: (2024)

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
by: Peng, Xiaoxuan, et al.
Published: (2026)

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
by: Xu, Ruoxi, et al.
Published: (2025)

ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch
by: Chen, Jiawei, et al.
Published: (2025)

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models
by: Zheng, Jiasheng, et al.
Published: (2026)

StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation
by: Cao, Boxi, et al.
Published: (2024)

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
by: Yuan, Qianhao, et al.
Published: (2025)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
by: Tang, Qiaoyu, et al.
Published: (2024)

P^2O: Joint Policy and Prompt Optimization
by: Lu, Xinyu, et al.
Published: (2026)

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models
by: Xiang, Hao, et al.
Published: (2024)

Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards
by: Ren, Mengjie, et al.
Published: (2026)

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
by: Wang, Dan, et al.
Published: (2026)

Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering
by: Chen, Xiaoyang, et al.
Published: (2024)

Coupled Variational Reinforcement Learning for Language Model General Reasoning
by: Wen, Xueru, et al.
Published: (2025)

ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
by: Bian, Ning, et al.
Published: (2023)

Towards Universal Dense Blocking for Entity Resolution
by: Wang, Tianshu, et al.
Published: (2024)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
by: Yuan, Qianhao, et al.
Published: (2026)

URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
by: Li, Zhuoqun, et al.
Published: (2024)

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

Open Grounded Planning: Challenges and Benchmark Construction
by: Guo, Shiguang, et al.
Published: (2024)

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
by: Zheng, Hao, et al.
Published: (2025)

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
by: Liu, Yanjiang, et al.
Published: (2026)

Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
by: Chen, Jiawei, et al.
Published: (2026)

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model
by: Chen, Jiawei, et al.
Published: (2024)

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
by: Yuan, Qianhao, et al.
Published: (2025)

Learning or Self-aligning? Rethinking Instruction Fine-tuning
by: Ren, Mengjie, et al.
Published: (2024)

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models
by: Liang, Qiao, et al.
Published: (2025)