Image de couverture de livre

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Shuozhe, Cao, Jincheng, Hu, Bodun, Mokhtari, Aryan, Liu, Leqi, Zhang, Amy
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Curriculum Learning-Guided Progressive Distillation in Large Language Models
par: Cao, Jincheng, et autres
Publié: (2026)

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
par: Pathak, Manas, et autres
Publié: (2026)

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
par: Zhou, Ruiyang, et autres
Publié: (2025)

A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization
par: Li, Shuozhe, et autres
Publié: (2026)

Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model
par: Liang, Jing, et autres
Publié: (2025)

Vanishing Gradients in Reinforcement Finetuning of Language Models
par: Razin, Noam, et autres
Publié: (2023)

Large Language Models to Diffusion Finetuning
par: Cetin, Edoardo, et autres
Publié: (2025)

Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
par: Liu, Z, et autres
Publié: (2024)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
par: Stengel-Eskin, Elias, et autres
Publié: (2024)

Prompting Fairness: Integrating Causality to Debias Large Language Models
par: Li, Jingling, et autres
Publié: (2024)

Transfer Learning of Tabular Data by Finetuning Large Language Models
par: Rabbani, Shourav B., et autres
Publié: (2025)

Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
par: Ma, Zhengzhao, et autres
Publié: (2026)

Personalized Language Modeling from Personalized Human Feedback
par: Li, Xinyu, et autres
Publié: (2024)

Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
par: Zhang, Andi, et autres
Publié: (2024)

A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
par: Zhang, Junjie, et autres
Publié: (2025)

Early Stopping for Large Reasoning Models via Confidence Dynamics
par: Hosseini, Parsa, et autres
Publié: (2026)

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
par: Bello, Femi, et autres
Publié: (2025)

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
par: Kumar, Abhishek, et autres
Publié: (2024)

Learning Robust Reasoning through Guided Adversarial Self-Play
par: Li, Shuozhe, et autres
Publié: (2026)

Advancing Reasoning in Large Language Models: Promising Methods and Approaches
par: Patil, Avinash, et autres
Publié: (2025)

QOG:Question and Options Generation based on Language Model
par: Zhou, Jincheng
Publié: (2024)

Large Language Models aren't all that you need
par: Holla, Kiran Voderhobli, et autres
Publié: (2024)

Reinforcement Learning for Reasoning in Large Language Models with One Training Example
par: Wang, Yiping, et autres
Publié: (2025)

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
par: Collins, Liam, et autres
Publié: (2024)

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
par: Bhatt, Gantavya, et autres
Publié: (2024)

Confidence-Modulated Speculative Decoding for Large Language Models
par: Sen, Jaydip, et autres
Publié: (2025)

ReFT: Representation Finetuning for Language Models
par: Wu, Zhengxuan, et autres
Publié: (2024)

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning
par: Wang, Yongxin, et autres
Publié: (2025)

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
par: Xi, Zhiheng, et autres
Publié: (2024)

Delta Activations: A Representation for Finetuned Large Language Models
par: Xu, Zhiqiu, et autres
Publié: (2025)

Graph-based Confidence Calibration for Large Language Models
par: Li, Yukun, et autres
Publié: (2024)

An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning
par: Xu, Haoran, et autres
Publié: (2025)

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
par: Chen, Yi, et autres
Publié: (2025)

Small or Large? Zero-Shot or Finetuned? Guiding Language Model Choice for Specialized Applications in Healthcare
par: Gondara, Lovedeep, et autres
Publié: (2025)

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
par: Yeh, Cheng-Kai, et autres
Publié: (2025)

A Survey of Reinforcement Learning for Large Reasoning Models
par: Zhang, Kaiyan, et autres
Publié: (2025)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
par: Jin, Renren, et autres
Publié: (2025)

A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
par: Yuan, Hui, et autres
Publié: (2024)

Large Language Model Confidence Estimation via Black-Box Access
par: Pedapati, Tejaswini, et autres
Publié: (2024)

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
par: Liu, Yuliang, et autres
Publié: (2025)