Cover Image

Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Yuyi, Zhan, Runzhe, Chao, Lidia S., Tao, Ailin, Wong, Derek F.
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

Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models
by: Huang, Yuyi, et al.
Published: (2025)

Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model
by: Xu, Haoyun, et al.
Published: (2024)

Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
by: Zhan, Runzhe, et al.
Published: (2025)

Rethinking Prompt-based Debiasing in Large Language Models
by: Yang, Xinyi, et al.
Published: (2025)

Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model
by: Zhan, Runzhe, et al.
Published: (2024)

Neuron-Aware Data Selection In Instruction Tuning For Large Language Models
by: Chen, Xin, et al.
Published: (2026)

A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions
by: Wu, Junchao, et al.
Published: (2023)

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning
by: Ma, Jingkun, et al.
Published: (2024)

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore
by: Wu, Junchao, et al.
Published: (2024)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
by: Wu, Junchao, et al.
Published: (2024)

Overriding Safety protections of Open-source Models
by: Kumar, Sachin
Published: (2024)

Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
by: Sun, Yanming, et al.
Published: (2025)

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
by: Li, Yubo, et al.
Published: (2026)

ExGRPO: Learning to Reason from Experience
by: Zhan, Runzhe, et al.
Published: (2025)

RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
by: Chen, Xin, et al.
Published: (2025)

A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU
by: Chen, Guanhua, et al.
Published: (2024)

Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning
by: Wang, Zhilin, et al.
Published: (2025)

Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination
by: He, Xiaoqi, et al.
Published: (2026)

Can ChatGPT Really Understand Modern Chinese Poetry?
by: Wang, Shanshan, et al.
Published: (2026)

What is the Best Way for ChatGPT to Translate Poetry?
by: Wang, Shanshan, et al.
Published: (2024)

Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence
by: Ye, Fengying, et al.
Published: (2025)

FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models
by: Lan, Kaixin, et al.
Published: (2024)

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study
by: Zhang, Zhexin, et al.
Published: (2025)

Nevermind: Instruction Override and Moderation in Large Language Models
by: Kim, Edward
Published: (2024)

SGIC: A Self-Guided Iterative Calibration Framework for RAG
by: Chen, Guanhua, et al.
Published: (2025)

Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
by: Chen, Guanhua, et al.
Published: (2026)

Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?
by: Tam, Zhi Rui, et al.
Published: (2025)

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

From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG
by: Chen, Guanhua, et al.
Published: (2026)

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning
by: Zhang, Yanfang, et al.
Published: (2024)

Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
by: Luo, Sichun, et al.
Published: (2025)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
by: Lou, Xinyue, et al.
Published: (2025)

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist
by: Zhou, Zihao, et al.
Published: (2024)

Not All LoRA Parameters Are Essential: Insights on Inference Necessity
by: Chen, Guanhua, et al.
Published: (2025)

Educational Personalized Learning Path Planning with Large Language Models
by: Ng, Chee, et al.
Published: (2024)

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
by: Wang, Rui, et al.
Published: (2025)

Safety in Large Reasoning Models: A Survey
by: Wang, Cheng, et al.
Published: (2025)

Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry
by: Wang, Shanshan, et al.
Published: (2025)

The Better Angels of Machine Personality: How Personality Relates to LLM Safety
by: Zhang, Jie, et al.
Published: (2024)

Humanity in AI: Detecting the Personality of Large Language Models
by: Zhan, Baohua, et al.
Published: (2024)