Imagen de Portada

Exploiting Contextual Knowledge in LLMs through V-usable Information based Layer Enhancement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuan, Xiaowei, Yang, Zhao, Huang, Ziyang, Wang, Yequan, Fan, Siqi, Ju, Yiming, Zhao, Jun, Liu, Kang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent
por: Huang, Ziyang, et al.
Publicado: (2025)

Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint
por: Yuan, Xiaowei, et al.
Publicado: (2024)

Commonsense Knowledge Editing Based on Free-Text in LLMs
por: Huang, Xiusheng, et al.
Publicado: (2024)

Improving Zero-shot LLM Re-Ranker with Risk Minimization
por: Yuan, Xiaowei, et al.
Publicado: (2024)

Capability Localization: Capabilities Can be Localized rather than Individual Knowledge
por: Huang, Xiusheng, et al.
Publicado: (2025)

Not All Layers of LLMs Are Necessary During Inference
por: Fan, Siqi, et al.
Publicado: (2024)

Contextual Categorization Enhancement through LLMs Latent-Space
por: Bettouche, Zineddine, et al.
Publicado: (2024)

Speech LLMs are Contextual Reasoning Transcribers
por: Deng, Keqi, et al.
Publicado: (2026)

Towards Adaptive Mechanism Activation in Language Agent
por: Huang, Ziyang, et al.
Publicado: (2024)

LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation
por: Sun, Yang, et al.
Publicado: (2025)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
por: Fan, Siqi, et al.
Publicado: (2025)

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
por: Hu, Chenhui, et al.
Publicado: (2024)

Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
por: Tan, Yuqiao, et al.
Publicado: (2025)

SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
por: Xing, Xingrun, et al.
Publicado: (2024)

Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
por: Huang, Ziyang, et al.
Publicado: (2025)

Dual Encoder: Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction
por: Zhao, Xiaowei, et al.
Publicado: (2024)

Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency
por: Fan, Siqi, et al.
Publicado: (2025)

The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models
por: Fan, Siqi, et al.
Publicado: (2025)

EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
por: Cao, Pengfei, et al.
Publicado: (2025)

WideSeek: Advancing Wide Research via Multi-Agent Scaling
por: Huang, Ziyang, et al.
Publicado: (2026)

Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation
por: Shen, Jiajun, et al.
Publicado: (2025)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
por: Wang, Jianing, et al.
Publicado: (2023)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
por: Qi, Siya, et al.
Publicado: (2026)

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
por: Miao, Ziqi, et al.
Publicado: (2025)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
por: Ju, Yiming, et al.
Publicado: (2024)

Reasons and Solutions for the Decline in Model Performance after Editing
por: Huang, Xiusheng, et al.
Publicado: (2024)

Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation
por: Huang, Langlin, et al.
Publicado: (2024)

Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report
por: Du, Li, et al.
Publicado: (2025)

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
por: Kang, Minki, et al.
Publicado: (2024)

Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
por: Huang, Xiusheng, et al.
Publicado: (2026)

Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs
por: Zhu, Jiace, et al.
Publicado: (2024)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
por: Zhou, Yigeng, et al.
Publicado: (2026)

DiffuCOMET: Contextual Commonsense Knowledge Diffusion
por: Gao, Silin, et al.
Publicado: (2024)

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
por: Wang, Yilin, et al.
Publicado: (2025)

Multimodal Reasoning with Multimodal Knowledge Graph
por: Lee, Junlin, et al.
Publicado: (2024)

PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs
por: Zhao, Tianyu, et al.
Publicado: (2026)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
por: Tang, Zicong, et al.
Publicado: (2025)

Suicidal Comment Tree Dataset: Enhancing Risk Assessment and Prediction Through Contextual Analysis
por: Li, Jun, et al.
Publicado: (2025)

MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search
por: Yuan, Shuozhi, et al.
Publicado: (2025)

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
por: Hu, Chenhui, et al.
Publicado: (2024)