Image de couverture de livre

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pappone, Francesco, Lazzaroni, Ruggero Marino, Califano, Federico, Gentile, Niccolò, Marras, Roberto
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations
par: Lazzaroni, Ruggero Marino, et autres
Publié: (2025)

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
par: Tan, Hongze, et autres
Publié: (2025)

Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models
par: Pirozelli, Paulo, et autres
Publié: (2023)

Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO
par: Kattamuri, Ashish, et autres
Publié: (2025)

Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?
par: Roccabruna, Gabriel, et autres
Publié: (2024)

Combining Transformers with Natural Language Explanations
par: Ruggeri, Federico, et autres
Publié: (2021)

Infini-News: Efficiently Queryable Access to 1.3 Billion Processed Common Crawl News Articles
par: Lazzaroni, Ruggero Marino, et autres
Publié: (2026)

Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
par: Zhang, Yingji, et autres
Publié: (2022)

MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting
par: Wei, Kangda, et autres
Publié: (2026)

RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents
par: Zhong, Haitian, et autres
Publié: (2026)

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
par: Yang, Zixuan, et autres
Publié: (2026)

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
par: Zhang, Yudi, et autres
Publié: (2025)

Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
par: Bajaj, Anooshka, et autres
Publié: (2025)

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
par: Fein, Daniel, et autres
Publié: (2026)

From Spectra to Geography: Intelligent Mapping of RRUFF Mineral Data
par: Pappone, Francesco, et autres
Publié: (2024)

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
par: Zhang, Qingru, et autres
Publié: (2025)

Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanation
par: Wang, Qin, et autres
Publié: (2024)

Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
par: Sovrano, Francesco, et autres
Publié: (2026)

LLM Self-Explanations Fail Semantic Invariance
par: Szeider, Stefan
Publié: (2026)

Reward Shaping to Mitigate Reward Hacking in RLHF
par: Fu, Jiayi, et autres
Publié: (2025)

Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models
par: Maura-Rivero, Roberto-Rafael, et autres
Publié: (2025)

On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
par: Cai, Deng, et autres
Publié: (2024)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
par: Xie, Tianbao, et autres
Publié: (2023)

Reward Model Perspectives: Whose Opinions Do Reward Models Reward?
par: Elle
Publié: (2025)

Transformers and Cortical Waves: Encoders for Pulling In Context Across Time
par: Muller, Lyle, et autres
Publié: (2024)

LabelFusion: Fusing Large Language Models with Transformer Encoders for Robust Financial News Classification
par: Schlee, Michael, et autres
Publié: (2025)

Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
par: Zhang, Yingji, et autres
Publié: (2023)

Transformer-Encoder Trees for Efficient Multilingual Machine Translation and Speech Translation
par: Guan, Yiwen, et autres
Publié: (2025)

Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks
par: Yildirim, Savas
Publié: (2024)

Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER
par: Zhu, Junyi, et autres
Publié: (2025)

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward
par: An, Hao, et autres
Publié: (2025)

Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
par: Liu, Chris Yuhao, et autres
Publié: (2024)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
par: Zhang, Xiaoying, et autres
Publié: (2025)

Tiny Reward Models
par: Pan, Sarah
Publié: (2025)

Free(): Learning to Forget in Malloc-Only Reasoning Models
par: Zheng, Yilun, et autres
Publié: (2026)

M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
par: Bai, Bizhe, et autres
Publié: (2025)

GRAM: A Generative Foundation Reward Model for Reward Generalization
par: Wang, Chenglong, et autres
Publié: (2025)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
par: Liu, Yang, et autres
Publié: (2026)

WildReward: Learning Reward Models from In-the-Wild Human Interactions
par: Peng, Hao, et autres
Publié: (2026)

Layer-Wise Evolution of Representations in Fine-Tuned Transformers: Insights from Sparse AutoEncoders
par: Nadipalli, Suneel
Publié: (2025)