Cover Image

Human-Instruction-Free LLM Self-Alignment with Limited Samples

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Hongyi, Yao, Yuanshun, Shen, Wei, Wei, Jiaheng, Zhang, Xiaoying, Wang, Zhaoran, Liu, Yang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
by: Shen, Wei, et al.
Published: (2024)

Measuring and Reducing LLM Hallucination without Gold-Standard Answers
by: Wei, Jiaheng, et al.
Published: (2024)

Toward Optimal LLM Alignments Using Two-Player Games
by: Zheng, Rui, et al.
Published: (2024)

ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
by: Estornell, Andrew, et al.
Published: (2024)

Large Language Model Unlearning
by: Yao, Yuanshun, et al.
Published: (2023)

On the Cause of Unfairness: A Training Sample Perspective
by: Yao, Yuanshun, et al.
Published: (2023)

Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation
by: Zheng, Tianyu, et al.
Published: (2024)

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
by: Jiang, Chunyang, et al.
Published: (2025)

Improving Data Efficiency via Curating LLM-Driven Rating Systems
by: Pang, Jinlong, 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)

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
by: Cai, Hongyi, et al.
Published: (2025)

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
by: Huang, Hui, et al.
Published: (2025)

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
by: Fu, Tingchen, et al.
Published: (2024)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
by: Zhang, Xiaoying, et al.
Published: (2024)

AIR: Complex Instruction Generation via Automatic Iterative Refinement
by: Liu, Wei, et al.
Published: (2025)

Think-J: Learning to Think for Generative LLM-as-a-Judge
by: Huang, Hui, et al.
Published: (2025)

Multilingual Safety Alignment via Self-Distillation
by: Qin, Ruiyang, et al.
Published: (2026)

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
by: Zhang, Ruohong, et al.
Published: (2023)

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
by: Pang, Jinlong, et al.
Published: (2025)

LLM Unlearning via Loss Adjustment with Only Forget Data
by: Wang, Yaxuan, et al.
Published: (2024)

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom
by: Li, Yisen, et al.
Published: (2025)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
by: Duan, Shitong, et al.
Published: (2024)

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback
by: Wu, Qinzhuo, et al.
Published: (2024)

Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
by: Cheng, Zehua, et al.
Published: (2026)

AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation
by: Liu, Xianyang, et al.
Published: (2025)

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
by: Wang, Yidong, et al.
Published: (2023)

Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization
by: Lu, Junjie, et al.
Published: (2025)

HumanLM: Simulating Users with State Alignment Beats Response Imitation
by: Wu, Shirley, et al.
Published: (2026)

Mind the Gap: The Divergence Between Human and LLM-Generated Tasks
by: Lu, Yi-Long, et al.
Published: (2025)

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
by: Liu, Yi, et al.
Published: (2025)

Unlocking the Power of Large Language Models for Entity Alignment
by: Jiang, Xuhui, et al.
Published: (2024)

xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
by: Chai, Linzheng, et al.
Published: (2024)

Evaluating Human Alignment and Model Faithfulness of LLM Rationale
by: Fayyaz, Mohsen, et al.
Published: (2024)

Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale
by: Li, Weiyue, et al.
Published: (2026)

DPRF: A Generalizable Dynamic Persona Refinement Framework for Optimizing Behavior Alignment Between Personalized LLM Role-Playing Agents and Humans
by: Yao, Bingsheng, et al.
Published: (2025)

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
by: Wang, Haoyu, et al.
Published: (2024)

Self-Review Framework for Enhancing Instruction Following Capability of LLM
by: Park, Sihyun
Published: (2025)

Towards Unified Alignment Between Agents, Humans, and Environment
by: Yang, Zonghan, et al.
Published: (2024)

Learning Personalized Agents from Human Feedback
by: Liang, Kaiqu, et al.
Published: (2026)

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
by: Huang, Yuqing, et al.
Published: (2025)