Copertina

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Zihao, Zhang, Hongbao, Wang, Ruotong, Xu, Ke, Lyu, Siwei, Wu, Baoyuan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
di: Zhu, Zihao, et al.
Pubblicazione: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
di: Wan, Xu, et al.
Pubblicazione: (2025)

AdaptThink: Reasoning Models Can Learn When to Think
di: Zhang, Jiajie, et al.
Pubblicazione: (2025)

Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
di: Jha, Basab, et al.
Pubblicazione: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
di: Guo, Zhenyuan, et al.
Pubblicazione: (2026)

MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
di: Xi, Ningyuan, et al.
Pubblicazione: (2024)

Effectively Controlling Reasoning Models through Thinking Intervention
di: Wu, Tong, et al.
Pubblicazione: (2025)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
di: Xu, Xin, et al.
Pubblicazione: (2026)

Efficient Reasoning with Hidden Thinking
di: Shen, Xuan, et al.
Pubblicazione: (2025)

Efficient Reasoning with Balanced Thinking
di: Li, Yulin, et al.
Pubblicazione: (2026)

Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework
di: Wu, Guanzong, et al.
Pubblicazione: (2026)

BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
di: Zhong, Han, et al.
Pubblicazione: (2025)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
di: Wang, Shouren, et al.
Pubblicazione: (2025)

Reasoning Models Don't Always Say What They Think
di: Chen, Yanda, et al.
Pubblicazione: (2025)

Reverse Thinking Makes LLMs Stronger Reasoners
di: Chen, Justin Chih-Yao, et al.
Pubblicazione: (2024)

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models
di: Wang, Xiao
Pubblicazione: (2026)

SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning
di: He, Zelin, et al.
Pubblicazione: (2026)

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
di: Li, Ming, et al.
Pubblicazione: (2025)

CoRT: Code-integrated Reasoning within Thinking
di: Li, Chengpeng, et al.
Pubblicazione: (2025)

Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents
di: Yu, Xiao, et al.
Pubblicazione: (2025)

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
di: Chen, Zhikang, et al.
Pubblicazione: (2025)

HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing
di: Zhu, Zihao, et al.
Pubblicazione: (2024)

Process Reward Models That Think
di: Khalifa, Muhammad, et al.
Pubblicazione: (2025)

Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models
di: Wang, Ziyan, et al.
Pubblicazione: (2025)

Reasoning with Sampling: Your Base Model is Smarter Than You Think
di: Karan, Aayush, et al.
Pubblicazione: (2025)

BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
di: Zhu, Zihao, et al.
Pubblicazione: (2026)

Learning When to Think While Listening in Large Audio-Language Models
di: Song, Zhiyuan, et al.
Pubblicazione: (2026)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
di: Fan, Chenrui, et al.
Pubblicazione: (2025)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
di: Wang, Kai, et al.
Pubblicazione: (2025)

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
di: Yang, Dayu, et al.
Pubblicazione: (2025)

Think Clearly: Improving Reasoning via Redundant Token Pruning
di: Choi, Daewon, et al.
Pubblicazione: (2025)

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
di: Tang, Yao, et al.
Pubblicazione: (2026)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
di: Sheshanarayana, Disha, et al.
Pubblicazione: (2026)

Agents Thinking Fast and Slow: A Talker-Reasoner Architecture
di: Christakopoulou, Konstantina, et al.
Pubblicazione: (2024)

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
di: Kohli, Harsh, et al.
Pubblicazione: (2026)

Think Before You Lie: How Reasoning Leads to Honesty
di: Yuan, Ann, et al.
Pubblicazione: (2026)

Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models
di: Xie, Zhifei, et al.
Pubblicazione: (2025)

Think When You Need: Self-Adaptive Chain-of-Thought Learning
di: Yang, Junjie, et al.
Pubblicazione: (2025)

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
di: Shojaee, Parshin, et al.
Pubblicazione: (2025)