Copertina

Reward Prediction with Factorized World States

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shen, Yijun, Chen, Delong, Hu, Xianming, Mi, Jiaming, Zhao, Hongbo, Zhang, Kai, Fung, Pascale
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Measuring Political Bias in Large Language Models: What Is Said and How It Is Said
di: Bang, Yejin, et al.
Pubblicazione: (2024)

LLM Internal States Reveal Hallucination Risk Faced With a Query
di: Ji, Ziwei, et al.
Pubblicazione: (2024)

Subobject-level Image Tokenization
di: Chen, Delong, et al.
Pubblicazione: (2024)

WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning
di: Chen, Delong, et al.
Pubblicazione: (2025)

High-Dimension Human Value Representation in Large Language Models
di: Cahyawijaya, Samuel, et al.
Pubblicazione: (2024)

Entropy Centroids as Intrinsic Rewards for Test-Time Scaling
di: Zhao, Wenshuo, et al.
Pubblicazione: (2026)

Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions
di: Shen, Yijun, et al.
Pubblicazione: (2025)

LLMs Are Few-Shot In-Context Low-Resource Language Learners
di: Cahyawijaya, Samuel, et al.
Pubblicazione: (2024)

High-Dimensional Interlingual Representations of Large Language Models
di: Wilie, Bryan, et al.
Pubblicazione: (2025)

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling
di: Zheng, Hang, et al.
Pubblicazione: (2025)

DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking in Long-Context Dialogue
di: Liao, Yijun
Pubblicazione: (2025)

Belief Revision: The Adaptability of Large Language Models Reasoning
di: Wilie, Bryan, et al.
Pubblicazione: (2024)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
di: Su, Yi, et al.
Pubblicazione: (2025)

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

Generative Deduplication For Socia Media Data Selection
di: Li, Xianming, et al.
Pubblicazione: (2024)

BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings
di: Li, Xianming, et al.
Pubblicazione: (2023)

Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
di: Lovenia, Holy, et al.
Pubblicazione: (2023)

Learning Ordinal Probabilistic Reward from Preferences
di: Chen, Longze, et al.
Pubblicazione: (2026)

Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios
di: Zang, Jianxiang, et al.
Pubblicazione: (2025)

Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation
di: Shen, Jiaming, et al.
Pubblicazione: (2024)

CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards
di: Lin, Zhiming, et al.
Pubblicazione: (2025)

Survey of Hallucination in Natural Language Generation
di: Ji, Ziwei, et al.
Pubblicazione: (2022)

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)

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models
di: Tang, Zecheng, et al.
Pubblicazione: (2026)

High-Fidelity Pruning for Large Language Models
di: Zhu, Yijun, et al.
Pubblicazione: (2026)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
di: Zhao, Weixiang, et al.
Pubblicazione: (2025)

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

Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards
di: Lyu, Yuanjie, et al.
Pubblicazione: (2026)

VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
di: Yan, Yuchen, et al.
Pubblicazione: (2025)

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
di: Zhang, Taolin, et al.
Pubblicazione: (2025)

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
di: Zhang, Qi, et al.
Pubblicazione: (2025)

Rewards as Labels: Revisiting RLVR from a Classification Perspective
di: Zhai, Zepeng, et al.
Pubblicazione: (2026)

Delusions of Large Language Models
di: Xu, Hongshen, et al.
Pubblicazione: (2025)

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
di: Ji, Ziwei, et al.
Pubblicazione: (2025)

Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
di: Ma, Qiyao, et al.
Pubblicazione: (2026)

SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
di: Tian, Yuanhe, et al.
Pubblicazione: (2026)

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
di: Zhang, Yi-Fan, et al.
Pubblicazione: (2025)

ProgRM: Build Better GUI Agents with Progress Rewards
di: Zhang, Danyang, et al.
Pubblicazione: (2025)

Towards Robust Process Reward Modeling via Noise-aware Learning
di: Xie, Bin, et al.
Pubblicazione: (2026)

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