Imagen de Portada

Improving Parametric Knowledge Access in Reasoning Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Melody, Hewitt, John
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

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

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
por: Yang, Wanli, et al.
Publicado: (2026)

Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts
por: Bandarkar, Lucas, et al.
Publicado: (2026)

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
por: Cheng, Sitao, et al.
Publicado: (2024)

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

Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation
por: Chen, Jinwen, et al.
Publicado: (2025)

Generating Tables from the Parametric Knowledge of Language Models
por: Berkovitch, Yevgeni, et al.
Publicado: (2024)

Re-Reading Improves Reasoning in Large Language Models
por: Xu, Xiaohan, et al.
Publicado: (2023)

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
por: Zhuo, Xingrui, et al.
Publicado: (2025)

Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning
por: Su, Xin, et al.
Publicado: (2023)

CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models
por: Chen, Yuefei, et al.
Publicado: (2025)

Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models
por: Ni, Shiwen, et al.
Publicado: (2023)

Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models
por: Hamdani, Rajaa El, et al.
Publicado: (2025)

Procedural Knowledge at Scale Improves Reasoning
por: Wu, Di, et al.
Publicado: (2026)

Subliminal Steering: Stronger Encoding of Hidden Signals
por: Morgulis, George, et al.
Publicado: (2026)

Knowledge Distillation for Temporal Knowledge Graph Reasoning with Large Language Models
por: Xing, Wang, et al.
Publicado: (2026)

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
por: Lin, Tzu-Han, et al.
Publicado: (2025)

Evaluating the External and Parametric Knowledge Fusion of Large Language Models
por: Zhang, Hao, et al.
Publicado: (2024)

Multidimensional Consistency Improves Reasoning in Language Models
por: Lai, Huiyuan, et al.
Publicado: (2025)

Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
por: Nemkova, Apollinaire Poli, et al.
Publicado: (2025)

Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
por: Liu, Shuqi, et al.
Publicado: (2025)

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
por: Cong, Youan, et al.
Publicado: (2024)

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
por: Kim, Minsung, et al.
Publicado: (2025)

Knowledge Vector of Logical Reasoning in Large Language Models
por: Wang, Zixuan, et al.
Publicado: (2026)

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
por: Wang, Jianing, et al.
Publicado: (2023)

Large Language Models are In-context Teachers for Knowledge Reasoning
por: Zhao, Jiachen, et al.
Publicado: (2023)

UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge
por: Kim, Youna, et al.
Publicado: (2025)

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
por: Luo, Linhao, et al.
Publicado: (2024)

Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality
por: Zhang, Mike, et al.
Publicado: (2025)

Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models
por: Klisura, Đorđe, et al.
Publicado: (2025)

Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
por: Ding, Wenxuan, et al.
Publicado: (2023)

StressEval: Failure-Driven Dynamic Benchmarking for Knowledge-Intensive Reasoning in Large Language Models
por: Chen, Yongrui, et al.
Publicado: (2026)

Large Language Models Are Cross-Lingual Knowledge-Free Reasoners
por: Hu, Peng, et al.
Publicado: (2024)

Large Language Models are Limited in Out-of-Context Knowledge Reasoning
por: Hu, Peng, et al.
Publicado: (2024)

KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
por: Guo, Tiezheng, et al.
Publicado: (2023)

Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data
por: Kusuma, Christopher Adrian, et al.
Publicado: (2026)

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models
por: Pang, Xinyu, et al.
Publicado: (2024)

Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
por: Chae, Hyungjoo, et al.
Publicado: (2024)

Information Re-Organization Improves Reasoning in Large Language Models
por: Cheng, Xiaoxia, et al.
Publicado: (2024)

Refining Answer Distributions for Improved Large Language Model Reasoning
por: Pal, Soumyasundar, et al.
Publicado: (2024)