Image de couverture de livre

Rethinking Diverse Human Preference Learning through Principal Component Analysis

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luo, Feng, Yang, Rui, Sun, Hao, Deng, Chunyuan, Yao, Jiarui, Shen, Jingyan, Zhang, Huan, Chen, Hanjie
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence 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

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
par: Shen, Jingyan, et autres
Publié: (2025)

Learning Distribution-Wise Control in Representation Space for Language Models
par: Deng, Chunyuan, et autres
Publié: (2025)

Steering Information Utility in Key-Value Memory for Language Model Post-Training
par: Deng, Chunyuan, et autres
Publié: (2025)

The Generalization Ridge: Information Flow in Natural Language Generation
par: Chang, Ruidi, et autres
Publié: (2025)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
par: You, Zejia, et autres
Publié: (2026)

Language Models are Symbolic Learners in Arithmetic
par: Deng, Chunyuan, et autres
Publié: (2024)

SAFR: Neuron Redistribution for Interpretability
par: Chang, Ruidi, et autres
Publié: (2025)

Rethinking Human Preference Evaluation of LLM Rationales
par: Li, Ziang, et autres
Publié: (2025)

PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation
par: Chang, Ruidi, et autres
Publié: (2026)

Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction
par: Murawaki, Yugo
Publié: (2024)

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?
par: Zhou, Jingyan, et autres
Publié: (2023)

Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design
par: Xiao, Yunze, et autres
Publié: (2025)

LT2: Linear-Time Looped Transformers
par: Deng, Chunyuan, et autres
Publié: (2026)

Diverse Preference Optimization
par: Lanchantin, Jack, et autres
Publié: (2025)

BATON: Aligning Text-to-Audio Model with Human Preference Feedback
par: Liao, Huan, et autres
Publié: (2024)

Robust Bayesian Functional Principal Component Analysis
par: Zhang, Jiarui, et autres
Publié: (2023)

From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition
par: Yang, Qiyuan, et autres
Publié: (2024)

LRHP: Learning Representations for Human Preferences via Preference Pairs
par: Wang, Chenglong, et autres
Publié: (2024)

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
par: Peng, Andi, et autres
Publié: (2024)

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
par: Han, Yang, et autres
Publié: (2024)

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
par: Sun, Yifan, et autres
Publié: (2025)

FaiMA: Feature-aware In-context Learning for Multi-domain Aspect-based Sentiment Analysis
par: Yang, Songhua, et autres
Publié: (2024)

Diverse Preference Learning for Capabilities and Alignment
par: Slocum, Stewart, et autres
Publié: (2025)

LiPO: Listwise Preference Optimization through Learning-to-Rank
par: Liu, Tianqi, et autres
Publié: (2024)

COPR: Continual Learning Human Preference through Optimal Policy Regularization
par: Zhang, Han, et autres
Publié: (2023)

Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
par: Shen, Wei, et autres
Publié: (2024)

A Survey on Human Preference Learning for Large Language Models
par: Jiang, Ruili, et autres
Publié: (2024)

Learning Ordinal Probabilistic Reward from Preferences
par: Chen, Longze, et autres
Publié: (2026)

VRM: Teaching Reward Models to Understand Authentic Human Preferences
par: Liu, Biao, et autres
Publié: (2026)

MaxMin-RLHF: Alignment with Diverse Human Preferences
par: Chakraborty, Souradip, et autres
Publié: (2024)

ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
par: Deng, Chunyuan, et autres
Publié: (2026)

Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
par: Tang, Raphael, et autres
Publié: (2025)

GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
par: Fang, Zhouxiang, et autres
Publié: (2026)

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
par: Wang, Haoxiang, et autres
Publié: (2024)

Robust Principal Component Analysis via Discriminant Sample Weight Learning
par: Deng, Yingzhuo, et autres
Publié: (2024)

DeformAr: Rethinking NER Evaluation through Component Analysis and Visual Analytics
par: Younes, Ahmed Mustafa
Publié: (2025)

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
par: Feng, Jiarui, et autres
Publié: (2025)

When Reasoning Meets Its Laws
par: Zhang, Junyu, et autres
Publié: (2025)

Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
par: Yang, Sen, et autres
Publié: (2024)

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
par: Yang, Rui, et autres
Publié: (2024)