Copertina

BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yi, Biao, Fei, Zekun, Geng, Jianing, Li, Tong, Nie, Lihai, Liu, Zheli, Li, Yiming
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BadActs: A Universal Backdoor Defense in the Activation Space
di: Yi, Biao, et al.
Pubblicazione: (2024)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
di: Geng, Jianing, et al.
Pubblicazione: (2025)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
di: Fei, Zekun, et al.
Pubblicazione: (2024)

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
di: Yi, Biao, et al.
Pubblicazione: (2025)

Gradient Surgery for Safe LLM Fine-Tuning
di: Yi, Biao, et al.
Pubblicazione: (2025)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
di: Yi, Biao, et al.
Pubblicazione: (2025)

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
di: Guan, Weixin, et al.
Pubblicazione: (2026)

Prompt-Guided Internal States for Hallucination Detection of Large Language Models
di: Zhang, Fujie, et al.
Pubblicazione: (2024)

DRQA: Dynamic Reasoning Quota Allocation for Controlling Overthinking in Reasoning Large Language Models
di: Yan, Kaiwen, et al.
Pubblicazione: (2025)

Mitigating Overthinking through Reasoning Shaping
di: Song, Feifan, et al.
Pubblicazione: (2025)

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
di: Sui, Yang, et al.
Pubblicazione: (2025)

Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models
di: Srivastava, Saurabh, et al.
Pubblicazione: (2025)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
di: Han, Jinyi, et al.
Pubblicazione: (2025)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
di: Huang, Yao, et al.
Pubblicazione: (2025)

Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis
di: Vamvourellis, Dimitris, et al.
Pubblicazione: (2025)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
di: Liu, Shuaitong, et al.
Pubblicazione: (2025)

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
di: Pu, Xiao, et al.
Pubblicazione: (2025)

Analyzing 16,193 LLM Papers for Fun and Profits
di: Xia, Zhiqiu, et al.
Pubblicazione: (2025)

Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
di: Wang, Qianyue, et al.
Pubblicazione: (2026)

Unboxing Virgil ADTs for Fun and Profit
di: Teo, Bradley Wei Jie, et al.
Pubblicazione: (2024)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
di: Tong, Terry, et al.
Pubblicazione: (2025)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
di: Wei, Zihao, et al.
Pubblicazione: (2025)

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
di: Diao, Xingjian, et al.
Pubblicazione: (2026)

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

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
di: Wu, Zhengxian, et al.
Pubblicazione: (2025)

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
di: Li, Changyi, et al.
Pubblicazione: (2025)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
di: Jedidi, Nour, et al.
Pubblicazione: (2025)

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
di: Srivastava, Gaurav, et al.
Pubblicazione: (2025)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
di: Wang, Zihan, et al.
Pubblicazione: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
di: Hassid, Michael, et al.
Pubblicazione: (2025)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
di: Su, Jinyan, et al.
Pubblicazione: (2025)

Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
di: Wang, Jianing, et al.
Pubblicazione: (2023)

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
di: Yadav, Anushka, et al.
Pubblicazione: (2025)

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning
di: Wang, Jianing, et al.
Pubblicazione: (2025)

Practical Poisoning Attacks against Retrieval-Augmented Generation
di: Zhang, Baolei, et al.
Pubblicazione: (2025)

Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
di: Liu, Runxuan, et al.
Pubblicazione: (2026)

TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking
di: Wang, Danqing, et al.
Pubblicazione: (2024)

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
di: He, Junlin, et al.
Pubblicazione: (2026)

Progressively Label Enhancement for Large Language Model Alignment
di: Liu, Biao, et al.
Pubblicazione: (2024)