Imagen de Portada

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Maotian, Zeng, Zheni, Liu, Zhenghao, Yan, Yukun
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases
por: Zeng, Zheni, et al.
Publicado: (2024)

PersLLM: A Personified Training Approach for Large Language Models
por: Zeng, Zheni, et al.
Publicado: (2024)

DrugR: Optimizing Molecular Drugs through LLM-based Explicit Reasoning
por: Liu, Haoran, et al.
Publicado: (2026)

Empirical Analysis of Decoding Biases in Masked Diffusion Models
por: Huang, Pengcheng, et al.
Publicado: (2025)

NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
por: Dai, Jihao, et al.
Publicado: (2026)

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
por: Chen, Hao, et al.
Publicado: (2026)

DeepEdit: Knowledge Editing as Decoding with Constraints
por: Wang, Yiwei, et al.
Publicado: (2024)

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
por: Huang, Pengcheng, et al.
Publicado: (2025)

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
por: Wu, Mingyan, et al.
Publicado: (2025)

How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency
por: Zheng, Danna, et al.
Publicado: (2024)

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
por: Yao, Jui-Ming, et al.
Publicado: (2025)

Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models
por: Xiong, Guangzhi, et al.
Publicado: (2024)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
por: Lu, Yuyin, et al.
Publicado: (2026)

XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
por: Chen, Zichen, et al.
Publicado: (2023)

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
por: Wu, Shanglin, et al.
Publicado: (2025)

Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders
por: Zhu, Xiaofeng, et al.
Publicado: (2024)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
por: Phan, Phuc, et al.
Publicado: (2024)

Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
por: Kumar, Adarsh, et al.
Publicado: (2025)

Reinforcement Learning Improves Traversal of Hierarchical Knowledge in LLMs
por: Zhang, Renfei, et al.
Publicado: (2025)

Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation
por: Li, Xinze, et al.
Publicado: (2026)

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
por: Cui, Chengming, et al.
Publicado: (2026)

LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
por: Guo, Pei-Fu, et al.
Publicado: (2025)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
por: Liu, Shuliang, et al.
Publicado: (2025)

Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach
por: Zhang, Yukun
Publicado: (2024)

Dynamic Depth Decoding: Faster Speculative Decoding for LLMs
por: Brown, Oscar, et al.
Publicado: (2024)

PAD: Personalized Alignment of LLMs at Decoding-Time
por: Chen, Ruizhe, et al.
Publicado: (2024)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
por: Lin, Gang, et al.
Publicado: (2026)

Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
por: Kietkajornrit, Auksarapak, et al.
Publicado: (2026)

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
por: Li, Fengze, et al.
Publicado: (2025)

Improving Long Text Understanding with Knowledge Distilled from Summarization Model
por: Liu, Yan, et al.
Publicado: (2024)

HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
por: Jiang, Xinke, et al.
Publicado: (2023)

ICDM 2020 Knowledge Graph Contest: Consumer Event-Cause Extraction
por: He, Congqing, et al.
Publicado: (2021)

Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs
por: Vladika, Juraj, et al.
Publicado: (2025)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
por: Zhou, Yongchao, et al.
Publicado: (2023)

Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs
por: Ma, Huanhuan, et al.
Publicado: (2025)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
por: Lin, Ailiang, et al.
Publicado: (2025)

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs
por: Sun, Chenxi, et al.
Publicado: (2024)

How Open Must Language Models be to Enable Reliable Scientific Inference?
por: Michaelov, James A., et al.
Publicado: (2026)

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
por: Duan, Shaohua, et al.
Publicado: (2025)

Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss
por: Cai, Zhuoang, et al.
Publicado: (2025)