Image de couverture de livre

PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Xue, Yongfu
Format:	Preprint
Publié:	2025
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

Optimizing Fine-Tuning through Advanced Initialization Strategies for Low-Rank Adaptation
par: Xue, Yongfu
Publié: (2025)

ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning
par: Wu, Yang, et autres
Publié: (2024)

EVIT: Event-Oriented Instruction Tuning for Event Reasoning
par: Tao, Zhengwei, et autres
Publié: (2024)

Dual Instruction Tuning with Large Language Models for Mathematical Reasoning
par: Zhou, Yongwei, et autres
Publié: (2024)

Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models
par: Fan, Yuchen, et autres
Publié: (2024)

InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment
par: Wang, Jianing, et autres
Publié: (2024)

MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning
par: Bai, Yi, et autres
Publié: (2026)

Weighted-Reward Preference Optimization for Implicit Model Fusion
par: Yang, Ziyi, et autres
Publié: (2024)

RA-DIT: Retrieval-Augmented Dual Instruction Tuning
par: Lin, Xi Victoria, et autres
Publié: (2023)

Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models
par: Hayati, Shirley Anugrah, et autres
Publié: (2024)

EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences
par: Ghate, Kshitish, et autres
Publié: (2025)

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

Spec-TOD: A Specialized Instruction-Tuned LLM Framework for Efficient Task-Oriented Dialogue Systems
par: Nguyen, Quang-Vinh, et autres
Publié: (2025)

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
par: Xue, Tianci, et autres
Publié: (2023)

Instruction Following without Instruction Tuning
par: Hewitt, John, et autres
Publié: (2024)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
par: Wen, Bosi, et autres
Publié: (2026)

Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models
par: Li, Shengzhi, et autres
Publié: (2024)

Robust Preference Optimization through Reward Model Distillation
par: Fisch, Adam, et autres
Publié: (2024)

Generalizing Reward Modeling for Out-of-Distribution Preference Learning
par: Jia, Chen
Publié: (2024)

Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting
par: Wang, Rui, et autres
Publié: (2023)

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

ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling
par: Teng, Dechuan, et autres
Publié: (2026)

Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions?
par: Weber, Alexander Arno, et autres
Publié: (2024)

MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward Models
par: Li, Wenzhe, et autres
Publié: (2025)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
par: Ruan, Zhiwen, et autres
Publié: (2026)

Preference Poisoning Attacks on Reward Model Learning
par: Wu, Junlin, et autres
Publié: (2024)

Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling
par: Tan, Shaomu, et autres
Publié: (2025)

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
par: Tao, Leitian, et autres
Publié: (2025)

Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation
par: Shen, Jiaming, et autres
Publié: (2024)

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
par: Zhu, Wenhong, et autres
Publié: (2024)

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
par: Peng, Hao, et autres
Publié: (2025)

Spivavtor: An Instruction Tuned Ukrainian Text Editing Model
par: Saini, Aman, et autres
Publié: (2024)

Bayesian Preference Learning for Test-Time Steerable Reward Models
par: Hong, Jiwoo, et autres
Publié: (2026)

Towards Understanding the Influence of Reward Margin on Preference Model Performance
par: Qin, Bowen, et autres
Publié: (2024)

Larger or Smaller Reward Margins to Select Preferences for Alignment?
par: Huang, Kexin, et autres
Publié: (2025)

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
par: Jin, Zhuoran, et autres
Publié: (2025)

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
par: Guo, Siqi, et autres
Publié: (2025)

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
par: Shu, Fangxun, et autres
Publié: (2025)

ARIA: Training Language Agents with Intention-Driven Reward Aggregation
par: Yang, Ruihan, et autres
Publié: (2025)

Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
par: Wang, Chenglong, et autres
Publié: (2025)