Cover Image

Course-Correction: Safety Alignment Using Synthetic Preferences

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Rongwu, Cai, Yishuo, Zhou, Zhenhong, Gu, Renjie, Weng, Haiqin, Liu, Yan, Zhang, Tianwei, Xu, Wei, Qiu, Han
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
by: Xu, Rongwu, et al.
Published: (2024)

Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
by: Xu, Rongwu
Published: (2024)

Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
by: Qi, Xuan, et al.
Published: (2025)

On the Role of Attention Heads in Large Language Model Safety
by: Zhou, Zhenhong, et al.
Published: (2024)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
by: Xu, Rongwu, et al.
Published: (2024)

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
by: Xu, Rongwu, et al.
Published: (2023)

Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation
by: Chen, Qiyuan, et al.
Published: (2025)

AI Awareness
by: Li, Xiaojian, et al.
Published: (2025)

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

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings
by: Liu, Tong, et al.
Published: (2025)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
by: Zhang, Xuemiao, et al.
Published: (2025)

Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
by: Xu, Rongwu, et al.
Published: (2025)

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
by: Liu, Quan, et al.
Published: (2024)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
by: Li, Guanlin, et al.
Published: (2025)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

Configurable Safety Tuning of Language Models with Synthetic Preference Data
by: Gallego, Victor
Published: (2024)

Sing it, Narrate it: Quality Musical Lyrics Translation
by: Ye, Zhuorui, et al.
Published: (2024)

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
by: Wang, Haoxiang, et al.
Published: (2024)

SafeWorld: Geo-Diverse Safety Alignment
by: Yin, Da, et al.
Published: (2024)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
by: Yang, Junxiao, et al.
Published: (2026)

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models
by: Liu, Biao, et al.
Published: (2025)

Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
by: Zhou, Zhenhong, et al.
Published: (2024)

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
by: Zhang, Yifan, et al.
Published: (2024)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
by: Su, Yanghao, et al.
Published: (2026)

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
by: Wu, Jiayi, et al.
Published: (2024)

EasyECR: A Library for Easy Implementation and Evaluation of Event Coreference Resolution Models
by: Li, Yuncong, et al.
Published: (2024)

Accelerated Preference Optimization for Large Language Model Alignment
by: He, Jiafan, et al.
Published: (2024)

Cat-DPO: Category-Adaptive Safety Alignment
by: Yang, Tiankai, et al.
Published: (2026)

Uncovering Factor Level Preferences to Improve Human-Model Alignment
by: Oh, Juhyun, et al.
Published: (2024)

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
by: Yang, Rui, et al.
Published: (2024)

Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
by: Nghiem, Huy, et al.
Published: (2025)

Safety Alignment via Constrained Knowledge Unlearning
by: Shi, Zesheng, et al.
Published: (2025)

SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
by: Kumar, Anurakt, et al.
Published: (2024)

Self-Boosting Large Language Models with Synthetic Preference Data
by: Dong, Qingxiu, et al.
Published: (2024)

A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
by: Xu, Yuemei, et al.
Published: (2024)

Intrinsic Test of Unlearning Using Parametric Knowledge Traces
by: Hong, Yihuai, et al.
Published: (2024)

Knowledge Conflicts for LLMs: A Survey
by: Xu, Rongwu, et al.
Published: (2024)

Self-Play Preference Optimization for Language Model Alignment
by: Wu, Yue, et al.
Published: (2024)

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
by: Xu, Jingxin, et al.
Published: (2025)