Image de couverture de livre

ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dong, Weilong, Wu, Xinwei, Jin, Renren, Xu, Shaoyang, Xiong, Deyi
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
par: Xu, Shaoyang, et autres
Publié: (2024)

IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
par: Shi, Dan, et autres
Publié: (2024)

Self-Pluralising Culture Alignment for Large Language Models
par: Xu, Shaoyang, et autres
Publié: (2024)

LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models
par: Liu, Chuang, et autres
Publié: (2024)

Do Large Language Models Mirror Cognitive Language Processing?
par: Ren, Yuqi, et autres
Publié: (2024)

Multilingual Large Language Models: A Systematic Survey
par: Zhu, Shaolin, et autres
Publié: (2024)

SOUP: Token-level Single-sample Mix-policy Reinforcement Learning for Large Language Models
par: Yang, Lei, et autres
Publié: (2026)

DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search
par: Yang, Lei, et autres
Publié: (2024)

FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models
par: Liu, Yan, et autres
Publié: (2024)

ProBench: Benchmarking Large Language Models in Competitive Programming
par: Yang, Lei, et autres
Publié: (2025)

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models
par: Shi, Dan, et autres
Publié: (2026)

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
par: Sun, Haoran, et autres
Publié: (2024)

Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation
par: Huang, Wuwei, et autres
Publié: (2025)

TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation
par: Jin, Renren, et autres
Publié: (2025)

A Comprehensive Evaluation of Quantization Strategies for Large Language Models
par: Jin, Renren, et autres
Publié: (2024)

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
par: Zhou, Hang, et autres
Publié: (2024)

OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
par: Liu, Chuang, et autres
Publié: (2024)

Large Language Model Safety: A Holistic Survey
par: Shi, Dan, et autres
Publié: (2024)

Improving Weak-to-Strong Generalization with Reliability-Aware Alignment
par: Guo, Yue, et autres
Publié: (2024)

Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons
par: Leng, Yongqi, et autres
Publié: (2024)

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting
par: Boateng, Emmanuel Aboah, et autres
Publié: (2024)

CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models
par: Shi, Ling, et autres
Publié: (2024)

Your Weak LLM is Secretly a Strong Teacher for Alignment
par: Tao, Leitian, et autres
Publié: (2024)

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
par: Fu, Yu, et autres
Publié: (2023)

MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
par: Lyu, Yougang, et autres
Publié: (2024)

Language of Thought Shapes Output Diversity in Large Language Models
par: Xu, Shaoyang, et autres
Publié: (2026)

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
par: Zhou, Jiang, et autres
Publié: (2026)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
par: Jin, Renren, et autres
Publié: (2025)

An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation
par: Supryadi, et autres
Publié: (2024)

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
par: Yang, Lei, et autres
Publié: (2025)

Evaluating Discourse Cohesion in Pre-trained Language Models
par: He, Jie, et autres
Publié: (2025)

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs
par: Wu, Xinwei, et autres
Publié: (2026)

Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
par: Li, Bo, et autres
Publié: (2026)

FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation
par: Zhu, Shaolin, et autres
Publié: (2025)

LFED: A Literary Fiction Evaluation Dataset for Large Language Models
par: Yu, Linhao, et autres
Publié: (2024)

W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search
par: Ding, Zhenyu, et autres
Publié: (2025)

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
par: Song, Feifan, et autres
Publié: (2025)

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
par: Yang, Lei, et autres
Publié: (2026)

Weak-to-Strong Reasoning
par: Yang, Yuqing, et autres
Publié: (2024)

Alice: Proactive Learning with Teacher's Demonstrations for Weak-to-Strong Generalization
par: Wu, Shujin, et autres
Publié: (2025)