Cover Image

Mitigating Deceptive Alignment via Self-Monitoring

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ji, Jiaming, Chen, Wenqi, Wang, Kaile, Hong, Donghai, Fang, Sitong, Chen, Boyuan, Zhou, Jiayi, Dai, Juntao, Han, Sirui, Guo, Yike, Yang, Yaodong
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
by: Fang, Sitong, et al.
Published: (2025)

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
by: Ji, Jiaming, et al.
Published: (2024)

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
by: Chen, Boyuan, et al.
Published: (2025)

Generative RLHF-V: Learning Principles from Multi-modal Human Preference
by: Zhou, Jiayi, et al.
Published: (2025)

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
by: Wen, Pengcheng, et al.
Published: (2025)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
by: Ji, Jiaming, et al.
Published: (2025)

Language Models Resist Alignment: Evidence From Data Compression
by: Ji, Jiaming, et al.
Published: (2024)

Aligner: Efficient Alignment by Learning to Correct
by: Ji, Jiaming, et al.
Published: (2024)

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
by: Fang, Sitong, et al.
Published: (2025)

Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction
by: Lou, Hantao, et al.
Published: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
by: Cao, Chuxue, et al.
Published: (2025)

SafeMT: Multi-turn Safety for Multimodal Language Models
by: Zhu, Han, et al.
Published: (2025)

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
by: Chen, Jiawei, et al.
Published: (2026)

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
by: Zhou, Jiayi, et al.
Published: (2024)

Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
by: Zhang, Guoxi, et al.
Published: (2026)

MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
by: Yang, Tianzhuo, et al.
Published: (2026)

AI Alignment: A Comprehensive Survey
by: Ji, Jiaming, et al.
Published: (2023)

SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence
by: Bu, Yuyan, et al.
Published: (2026)

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
by: Ji, Jiaming, et al.
Published: (2024)

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
by: Dai, Juntao, et al.
Published: (2025)

Benchmarking Multi-National Value Alignment for Large Language Models
by: Shi, Weijie, et al.
Published: (2025)

AI Deception: Risks, Dynamics, and Controls
by: Chen, Boyuan, et al.
Published: (2025)

A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
by: Zhang, Guoxi, et al.
Published: (2025)

Reward Generalization in RLHF: A Topological Perspective
by: Qiu, Tianyi, et al.
Published: (2024)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
by: Dai, Josef, et al.
Published: (2024)

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
by: Zhang, Borong, et al.
Published: (2025)

SAE-V: Interpreting Multimodal Models for Enhanced Alignment
by: Lou, Hantao, et al.
Published: (2025)

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning
by: Zhou, Yujin, et al.
Published: (2026)

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
by: Wang, Lichao, et al.
Published: (2026)

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
by: Chan, Chi-Min, et al.
Published: (2025)

Efficient Model-agnostic Alignment via Bayesian Persuasion
by: Bai, Fengshuo, et al.
Published: (2024)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
by: Ji, Jiaming, et al.
Published: (2023)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
by: Bu, Yuyan, et al.
Published: (2026)

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
by: Cao, Chuxue, et al.
Published: (2025)

Automate Strategy Finding with LLM in Quant Investment
by: Kou, Zhizhuo, et al.
Published: (2024)

Evolving Deception: When Agents Evolve, Deception Wins
by: Ying, Zonghao, et al.
Published: (2026)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
by: Zhang, Borong, et al.
Published: (2025)

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
by: Pan, Jiayi, et al.
Published: (2025)

When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models
by: Yakun, Cui, et al.
Published: (2026)

HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong
by: Han, Sirui, et al.
Published: (2025)