Copertina

Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zang, Jianxiang, Wei, Yongda, Bai, Ruxue, Jiang, Shiyu, Mo, Nijia, Li, Binhong, Sun, Qiang, Liu, Hui
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion
di: Zang, Jianxiang, et al.
Pubblicazione: (2025)

S2Sent: Nested Selectivity Aware Sentence Representation Learning
di: Zang, Jianxiang, et al.
Pubblicazione: (2025)

Alleviating Attention Hacking in Discriminative Reward Modeling through Interaction Distillation
di: Zang, Jianxiang
Pubblicazione: (2025)

Explanation based Bias Decoupling Regularization for Natural Language Inference
di: Zang, Jianxiang, et al.
Pubblicazione: (2024)

Modeling Selective Feature Attention for Representation-based Siamese Text Matching
di: Zang, Jianxiang, et al.
Pubblicazione: (2024)

Long-form RewardBench: Evaluating Reward Models for Long-form Generation
di: Huang, Hui, et al.
Pubblicazione: (2026)

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
di: Men, Tianyi, et al.
Pubblicazione: (2025)

Inference-Time Scaling for Generalist Reward Modeling
di: Liu, Zijun, et al.
Pubblicazione: (2025)

Small Reward Models via Backward Inference
di: Wang, Yike, et al.
Pubblicazione: (2026)

RRM: Robust Reward Model Training Mitigates Reward Hacking
di: Liu, Tianqi, et al.
Pubblicazione: (2024)

Consolidating Rewarded Perturbations for LLM Post-Training
di: Zhang, Zheyu, et al.
Pubblicazione: (2026)

Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
di: Li, Jiachun, et al.
Pubblicazione: (2025)

Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
di: Liu, Chris Yuhao, et al.
Pubblicazione: (2024)

Reward Model Perspectives: Whose Opinions Do Reward Models Reward?
di: Elle
Pubblicazione: (2025)

Reward Reasoning Model
di: Guo, Jiaxin, et al.
Pubblicazione: (2025)

RM-Distiller: Exploiting Generative LLM for Reward Model Distillation
di: Zhou, Hongli, et al.
Pubblicazione: (2026)

ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
di: Li, Xiaomin, et al.
Pubblicazione: (2025)

Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning
di: Mo, Shentong
Pubblicazione: (2026)

Reward Prediction with Factorized World States
di: Shen, Yijun, et al.
Pubblicazione: (2026)

On the Power of (Approximate) Reward Models for Inference-Time Scaling
di: Zhu, Youheng, et al.
Pubblicazione: (2026)

RewardBench 2: Advancing Reward Model Evaluation
di: Malik, Saumya, et al.
Pubblicazione: (2025)

Tool-Augmented Reward Modeling
di: Li, Lei, et al.
Pubblicazione: (2023)

RewardAnything: Generalizable Principle-Following Reward Models
di: Yu, Zhuohao, et al.
Pubblicazione: (2025)

Libra: Assessing and Improving Reward Model by Learning to Think
di: Zhou, Meng, et al.
Pubblicazione: (2025)

Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling
di: Pathmanathan, Pankayaraj, et al.
Pubblicazione: (2025)

PARM: Pipeline-Adapted Reward Model
di: Fan, Xingyu, et al.
Pubblicazione: (2026)

DocReward: A Document Reward Model for Structuring and Stylizing
di: Liu, Junpeng, et al.
Pubblicazione: (2025)

GRAM: A Generative Foundation Reward Model for Reward Generalization
di: Wang, Chenglong, et al.
Pubblicazione: (2025)

SteerRM: Debiasing Reward Models via Sparse Autoencoders
di: Sun, Mengyuan, et al.
Pubblicazione: (2026)

Dynamic and Generalizable Process Reward Modeling
di: Yin, Zhangyue, et al.
Pubblicazione: (2025)

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
di: Bai, Yang, et al.
Pubblicazione: (2026)

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model
di: Zang, Yuhang, et al.
Pubblicazione: (2025)

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
di: Wu, Keming, et al.
Pubblicazione: (2025)

From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
di: Jiang, Yuxin, et al.
Pubblicazione: (2026)

Inference Time Alignment with Reward-Guided Tree Search
di: Hung, Chia-Yu, et al.
Pubblicazione: (2024)

Towards Real-world Scenario: Imbalanced New Intent Discovery
di: Zhang, Shun, et al.
Pubblicazione: (2024)

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
di: Li, Lei, et al.
Pubblicazione: (2024)

ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
di: Sun, Zhongxiang, et al.
Pubblicazione: (2025)

StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios
di: Wang, Sizhe, et al.
Pubblicazione: (2026)

ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
di: Li, Shiyu, et al.
Pubblicazione: (2025)