Cover Image

Jailbreaking as a Reward Misspecification Problem

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Zhihui, Gao, Jiahui, Li, Lei, Li, Zhenguo, Liu, Qi, Kong, Lingpeng
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
by: Ye, Jiacheng, et al.
Published: (2024)

Teaching Language Models to Critique via Reinforcement Learning
by: Xie, Zhihui, et al.
Published: (2025)

A Reparameterized Discrete Diffusion Model for Text Generation
by: Zheng, Lin, et al.
Published: (2023)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
by: Ye, Jiacheng, et al.
Published: (2024)

Dream 7B: Diffusion Large Language Models
by: Ye, Jiacheng, et al.
Published: (2025)

Proxy Compression for Language Modeling
by: Zheng, Lin, et al.
Published: (2026)

PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models
by: Zhao, Xueliang, et al.
Published: (2025)

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
by: Zhao, Xueliang, et al.
Published: (2025)

Progressive-Hint Prompting Improves Reasoning in Large Language Models
by: Zheng, Chuanyang, et al.
Published: (2023)

Scaling Reasoning without Attention
by: Zhao, Xueliang, et al.
Published: (2025)

Self-Infilling Code Generation
by: Zheng, Lin, et al.
Published: (2023)

PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
by: Zhao, Xueliang, et al.
Published: (2025)

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
by: Yan, Lecheng, et al.
Published: (2026)

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
by: Li, Lei, et al.
Published: (2024)

Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
by: Xie, Zhihui, et al.
Published: (2024)

Testing the Limits of Jailbreaking Defenses with the Purple Problem
by: Kim, Taeyoun, et al.
Published: (2024)

Dream-Coder 7B: An Open Diffusion Language Model for Code
by: Xie, Zhihui, et al.
Published: (2025)

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
by: Wu, Zirui, et al.
Published: (2026)

Epistemic Traps: Rational Misalignment Driven by Model Misspecification
by: Xu, Xingcheng, et al.
Published: (2026)

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
by: Sun, Chung-En, et al.
Published: (2024)

Jailbreaking LLMs via Calibration
by: Lu, Yuxuan, et al.
Published: (2026)

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
by: Lyu, Chengqi, et al.
Published: (2025)

Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Models
by: Yu, Zichao, et al.
Published: (2025)

Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing
by: Yan, Yu, et al.
Published: (2025)

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
by: Geng, Jiahui, et al.
Published: (2025)

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
by: Zhang, Zhiwei, et al.
Published: (2025)

JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets
by: Jin, Zhihua, et al.
Published: (2024)

Implicit Search via Discrete Diffusion: A Study on Chess
by: Ye, Jiacheng, et al.
Published: (2025)

CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration
by: Gao, Jiahui, et al.
Published: (2024)

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
by: Hu, Zhiyuan, et al.
Published: (2026)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2026)

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
by: Huang, Guanhua, et al.
Published: (2025)

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
by: Ma, Qiyao, et al.
Published: (2026)

RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
by: Du, Yuhao, et al.
Published: (2025)

Reward Models Identify Consistency, Not Causality
by: Xu, Yuhui, et al.
Published: (2025)

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling
by: Li, Xiang, et al.
Published: (2026)

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
by: Gao, Jiahui, et al.
Published: (2023)

Jailbreaking LLMs with Arabic Transliteration and Arabizi
by: Ghanim, Mansour Al, et al.
Published: (2024)

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
by: Li, Qintong, et al.
Published: (2024)

Rewards as Labels: Revisiting RLVR from a Classification Perspective
by: Zhai, Zepeng, et al.
Published: (2026)