Cover Image

Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Ruopei, Cai, Jianfeng, Zhu, Jinhua, Zhao, Kangwen, Xue, Dongyun, Zhou, Wengang, Li, Li, Li, Houqiang
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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF
by: Zhao, Kangwen, et al.
Published: (2025)

CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation
by: Cai, Jianfeng, et al.
Published: (2026)

Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling
by: Cai, Jianfeng, et al.
Published: (2025)

Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning
by: Yu, Yan, et al.
Published: (2025)

Search-Based Credit Assignment for Offline Preference-Based Reinforcement Learning
by: Gao, Xiancheng, et al.
Published: (2025)

Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression
by: Tu, Hanyue, et al.
Published: (2025)

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning
by: Liu, Xiaoyang, et al.
Published: (2024)

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval
by: Xie, Xin, et al.
Published: (2026)

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

Robust Multimodal Large Language Models Against Modality Conflict
by: Zhang, Zongmeng, et al.
Published: (2025)

WPO: Enhancing RLHF with Weighted Preference Optimization
by: Zhou, Wenxuan, et al.
Published: (2024)

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

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
by: Cai, Jianfeng, et al.
Published: (2025)

Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models
by: Cui, Xiao, et al.
Published: (2024)

Self-supervised Hierarchical Visual Reasoning with World Model
by: Xu, Yuanfei, et al.
Published: (2026)

Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
by: Yu, Yan, et al.
Published: (2025)

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation
by: Li, Mingzhe, et al.
Published: (2025)

P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task
by: Xu, Weiye, et al.
Published: (2024)

Policy-labeled Preference Learning: Is Preference Enough for RLHF?
by: Cho, Taehyun, et al.
Published: (2025)

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
by: Zhen, Shuai, et al.
Published: (2026)

BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?
by: Zhang, Zongmeng, et al.
Published: (2024)

Progressive Multi-modal Conditional Prompt Tuning
by: Qiu, Xiaoyu, et al.
Published: (2024)

Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
by: Fan, Ziqing, et al.
Published: (2024)

Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
by: Zhang, Zongmeng, et al.
Published: (2024)

Multi-Treatment Multi-Task Uplift Modeling for Enhancing User Growth
by: Wei, Yuxiang, et al.
Published: (2024)

Tail-Aware Information-Theoretic Generalization for RLHF and SGLD
by: Zhang, Huiming, et al.
Published: (2026)

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
by: Li, Aaron J., et al.
Published: (2024)

Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discovery
by: Lan, Jing, et al.
Published: (2025)

Schema-Aware Multi-Task Learning for Complex Text-to-SQL
by: Wu, Yangjun, et al.
Published: (2024)

Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis
by: Sun, Qi, et al.
Published: (2024)

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

Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding
by: Sun, Qi, et al.
Published: (2024)

Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation
by: Huang, Hongzhe, et al.
Published: (2024)

Structure Similarity Preservation Learning for Asymmetric Image Retrieval
by: Wu, Hui, et al.
Published: (2024)

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models
by: Luan, Bozhi, et al.
Published: (2025)

Quantum-Enhanced Multi-Task Learning with Learnable Weighting for Pharmacokinetic and Toxicity Prediction
by: Zhang, Han, et al.
Published: (2025)

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

Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
by: Cui, Xiao, et al.
Published: (2025)

LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation
by: Zhou, Keyi, et al.
Published: (2024)

Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
by: Belakaria, Syrine, et al.
Published: (2025)