Imagen de Portada

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Wanli, Zang, Hongyu, Zhang, Junwei, Shi, Wenjie, Su, Du, Wang, Jingang, Cheng, Xueqi, Sun, Fei
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fine-tuning Done Right in Model Editing
por: Yang, Wanli, et al.
Publicado: (2025)

BaseCal: Unsupervised Confidence Calibration via Base Model Signals
por: Tan, Hexiang, et al.
Publicado: (2026)

Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
por: Gekhman, Zorik, et al.
Publicado: (2026)

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
por: Tan, Hexiang, et al.
Publicado: (2024)

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
por: Tan, Hexiang, et al.
Publicado: (2025)

Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement
por: Lin, Chenyu, et al.
Publicado: (2025)

RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
por: Xu, Shicheng, et al.
Publicado: (2025)

Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning
por: Jin, Song, et al.
Publicado: (2025)

Understanding the Collapse of LLMs in Model Editing
por: Yang, Wanli, et al.
Publicado: (2024)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
por: Deng, Wenhao, et al.
Publicado: (2025)

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs through Knowledge-Reasoning Fusion
por: Wu, Yutong, et al.
Publicado: (2025)

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
por: Wei, Wenda, et al.
Publicado: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
por: Xu, Hongling, et al.
Publicado: (2025)

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
por: Bi, Baolong, et al.
Publicado: (2024)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
por: Wei, Zihao, et al.
Publicado: (2025)

The Mirage of Model Editing: Revisiting Evaluation in the Wild
por: Yang, Wanli, et al.
Publicado: (2025)

R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
por: Chen, Yongchao, et al.
Publicado: (2025)

StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning
por: Guo, Yucan, et al.
Publicado: (2025)

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
por: Zhang, Xue, et al.
Publicado: (2025)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
por: Chen, Mingyang, et al.
Publicado: (2025)

Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
por: Huang, Shulin, et al.
Publicado: (2025)

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
por: Yue, Yang, et al.
Publicado: (2025)

Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication
por: Chen, Weize, et al.
Publicado: (2024)

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
por: Liu, Xiaoqian, et al.
Publicado: (2025)

BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning
por: Sun, Lin, et al.
Publicado: (2026)

MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
por: Yuan, Qianhao, et al.
Publicado: (2025)

Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning
por: Guo, Jiaxing, et al.
Publicado: (2025)

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
por: Zhou, Yixiao, et al.
Publicado: (2026)

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
por: Liu, Qin, et al.
Publicado: (2024)

KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
por: Wang, Shuai, et al.
Publicado: (2026)

Knowledge Graph Reasoning with Self-supervised Reinforcement Learning
por: Ma, Ying, et al.
Publicado: (2024)

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
por: Fan, Yuchun, et al.
Publicado: (2026)

HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning
por: Yang, Jinning, et al.
Publicado: (2025)

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
por: Li, Zhuoqun, et al.
Publicado: (2024)

eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs
por: Shi, Isaac, et al.
Publicado: (2025)

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
por: Liu, Zeyu, et al.
Publicado: (2025)

Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
por: Lin, Jiacheng, et al.
Publicado: (2025)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
por: Gao, Cheng, et al.
Publicado: (2026)

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
por: Zhou, Ruiyang, et al.
Publicado: (2025)

RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
por: Guo, Yucan, et al.
Publicado: (2025)