Copertina

CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Hao, Pan, Licheng, Chen, Zhichao, Zheng, Chunyuan, Chu, Zhixuan, Li, Xiaoxi, Lu, Yuan, Liu, Xinggao, Li, Haoxuan, Lin, Zhouchen
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
di: Wang, Hao, et al.
Pubblicazione: (2026)

DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
di: Wang, Hao, et al.
Pubblicazione: (2025)

Robust Reward Modeling for Large Language Models via Causal Decomposition
di: Lu, Yunsheng, et al.
Pubblicazione: (2026)

Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects
di: Wang, Hao, et al.
Pubblicazione: (2026)

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
di: Wang, Hao, et al.
Pubblicazione: (2025)

Deep Time-series Forecasting Needs Kernelized Moment Balancing
di: Pan, Licheng, et al.
Pubblicazione: (2026)

Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective
di: Chen, Zhichao, et al.
Pubblicazione: (2026)

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

Optimal Transport for LLM Reward Modeling from Noisy Preference
di: Pan, Licheng, et al.
Pubblicazione: (2026)

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
di: Wang, Hao, et al.
Pubblicazione: (2025)

Factored Causal Representation Learning for Robust Reward Modeling in RLHF
di: Yang, Yupei, et al.
Pubblicazione: (2026)

FreDF: Learning to Forecast in the Frequency Domain
di: Wang, Hao, et al.
Pubblicazione: (2024)

A Causal Perspective for Enhancing Jailbreak Attack and Defense
di: Pan, Licheng, et al.
Pubblicazione: (2026)

Debiased Collaborative Filtering with Kernel-Based Causal Balancing
di: Li, Haoxuan, et al.
Pubblicazione: (2024)

Entire Space Counterfactual Learning for Reliable Content Recommendations
di: Wang, Hao, et al.
Pubblicazione: (2022)

Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimation
di: Wang, Hao, et al.
Pubblicazione: (2024)

DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring
di: Wang, Hao, et al.
Pubblicazione: (2025)

Debiased Recommendation with Noisy Feedback
di: Li, Haoxuan, et al.
Pubblicazione: (2024)

Proactive Recommendation in Social Networks: Steering User Interest with Causal Inference
di: Pan, Hang, et al.
Pubblicazione: (2024)

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
di: Chen, Yang, et al.
Pubblicazione: (2024)

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement
di: Wang, Xiaobo, et al.
Pubblicazione: (2026)

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
di: Zhou, Jiayi, et al.
Pubblicazione: (2024)

Information-Theoretic Reward Decomposition for Generalizable RLHF
di: Mao, Liyuan, et al.
Pubblicazione: (2025)

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction
di: Chu, Zhixuan, et al.
Pubblicazione: (2023)

Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
di: Yang, Haotong, et al.
Pubblicazione: (2026)

Observationally Informed Adaptive Causal Experimental Design
di: Gao, Erdun, et al.
Pubblicazione: (2026)

Causal Interventional Prediction System for Robust and Explainable Effect Forecasting
di: Chu, Zhixuan, et al.
Pubblicazione: (2024)

Reward-Robust RLHF in LLMs
di: Yan, Yuzi, et al.
Pubblicazione: (2024)

A Causal Explainable Guardrails for Large Language Models
di: Chu, Zhixuan, et al.
Pubblicazione: (2024)

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
di: Miao, Yuchun, et al.
Pubblicazione: (2025)

A Theoretical Framework for Partially Observed Reward-States in RLHF
di: Kausik, Chinmaya, et al.
Pubblicazione: (2024)

How to Evaluate Reward Models for RLHF
di: Frick, Evan, et al.
Pubblicazione: (2024)

Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective
di: Chen, Zhichao, et al.
Pubblicazione: (2026)

VACT: A Video Automatic Causal Testing System and a Benchmark
di: Yang, Haotong, et al.
Pubblicazione: (2025)

RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders
di: Yang, Zhongheng, et al.
Pubblicazione: (2025)

Curious Causality-Seeking Agents Learn Meta Causal World
di: Zhao, Zhiyu, et al.
Pubblicazione: (2025)

Causally Robust Reward Learning from Reason-Augmented Preference Feedback
di: Hwang, Minjune, et al.
Pubblicazione: (2026)

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
di: Dai, Juntao, et al.
Pubblicazione: (2025)

Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
di: Pan, Licheng, et al.
Pubblicazione: (2025)

P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
di: Zhang, Pinyi, et al.
Pubblicazione: (2026)