Copertina

CHARM: Calibrating Reward Models With Chatbot Arena Scores

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Xiao, Tan, Chenmien, Chen, Pinzhen, Sennrich, Rico, Wang, Huiming, Zhang, Yanlin, Hu, Hanxu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
di: Zhu, Xiao, et al.
Pubblicazione: (2026)

Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models
di: Mohammadshahi, Alireza, et al.
Pubblicazione: (2023)

Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
di: Luo, Haipeng, et al.
Pubblicazione: (2024)

Improving Your Model Ranking on Chatbot Arena by Vote Rigging
di: Min, Rui, et al.
Pubblicazione: (2025)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
di: Wang, Chaoqi, et al.
Pubblicazione: (2025)

Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport
di: Ma, Rachel, et al.
Pubblicazione: (2026)

CalArena: A Large-Scale Post-Hoc Calibration Benchmark
di: Berta, Eugène, et al.
Pubblicazione: (2026)

Pairwise Calibrated Rewards for Pluralistic Alignment
di: Halpern, Daniel, et al.
Pubblicazione: (2025)

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
di: Park, Young-Jin, et al.
Pubblicazione: (2025)

SemiReward: A General Reward Model for Semi-supervised Learning
di: Li, Siyuan, et al.
Pubblicazione: (2023)

Reward Models in Deep Reinforcement Learning: A Survey
di: Yu, Rui, et al.
Pubblicazione: (2025)

XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation
di: Iyer, Vivek, et al.
Pubblicazione: (2025)

Learning a Diffusion Model Policy from Rewards via Q-Score Matching
di: Psenka, Michael, et al.
Pubblicazione: (2023)

Planning-Augmented Sampling with Early Guidance for High-Reward Discovery
di: Zhu, Rui, et al.
Pubblicazione: (2025)

Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
di: Foroutan, Negar, et al.
Pubblicazione: (2025)

CROP: Conservative Reward for Model-based Offline Policy Optimization
di: Li, Hao, et al.
Pubblicazione: (2023)

Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework
di: Deng, Yongxin, et al.
Pubblicazione: (2024)

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
di: Zhang, Yuheng, et al.
Pubblicazione: (2026)

Self-Generated Critiques Boost Reward Modeling for Language Models
di: Yu, Yue, et al.
Pubblicazione: (2024)

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
di: Xiao, Jiancong, et al.
Pubblicazione: (2025)

IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
di: Song, Haonan, et al.
Pubblicazione: (2026)

Reward-Directed Score-Based Diffusion Models via q-Learning
di: Gao, Xuefeng, et al.
Pubblicazione: (2024)

Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning
di: Xing, Jingyu, et al.
Pubblicazione: (2025)

Preference Poisoning Attacks on Reward Model Learning
di: Wu, Junlin, et al.
Pubblicazione: (2024)

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
di: Zhang, Qiang, et al.
Pubblicazione: (2026)

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning
di: Xia, Zixuan, et al.
Pubblicazione: (2026)

Massive Editing for Large Language Models via Meta Learning
di: Tan, Chenmien, et al.
Pubblicazione: (2023)

Complex Logical Query Answering by Calibrating Knowledge Graph Completion Models
di: Xiao, Changyi, et al.
Pubblicazione: (2024)

Saliency-Aware Regularized Quantization Calibration for Large Language Models
di: Zhao, Yanlong, et al.
Pubblicazione: (2026)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
di: Miao, Yuchun, et al.
Pubblicazione: (2024)

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models
di: Liu, Jincheng, et al.
Pubblicazione: (2025)

Enhancing Uplift Modeling in Multi-Treatment Marketing Campaigns: Leveraging Score Ranking and Calibration Techniques
di: Park, Yoon Tae, et al.
Pubblicazione: (2024)

Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling
di: Xie, Lipeng, et al.
Pubblicazione: (2025)

Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
di: Hu, Rui, et al.
Pubblicazione: (2025)

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

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
di: Lee, Jeongjae, et al.
Pubblicazione: (2026)

Automatically Finding Reward Model Biases
di: Wang, Atticus, et al.
Pubblicazione: (2026)

Intra-Trajectory Consistency for Reward Modeling
di: Zhou, Chaoyang, et al.
Pubblicazione: (2025)

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
di: Chen, Yang, et al.
Pubblicazione: (2025)

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking
di: Beigi, Mohammad, et al.
Pubblicazione: (2026)