Imagen de Portada

DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Lei, Xu, Shaoyang, Peng, Jianxiang, Zhu, Shaolin, Xiong, Deyi
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
por: Zhu, Shaolin, et al.
Publicado: (2024)

Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning
por: Cui, Menglong, et al.
Publicado: (2024)

Self-Pluralising Culture Alignment for Large Language Models
por: Xu, Shaoyang, et al.
Publicado: (2024)

Enhancing LLM Character-Level Manipulation via Divide and Conquer
por: Xiong, Zhen, et al.
Publicado: (2025)

ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
por: Dong, Weilong, et al.
Publicado: (2024)

Control Large Language Models via Divide and Conquer
por: Li, Bingxuan, et al.
Publicado: (2024)

Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
por: Li, Bo, et al.
Publicado: (2026)

FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation
por: Zhu, Shaolin, et al.
Publicado: (2025)

ProBench: Benchmarking Large Language Models in Competitive Programming
por: Yang, Lei, et al.
Publicado: (2025)

Multilingual Large Language Models: A Systematic Survey
por: Zhu, Shaolin, et al.
Publicado: (2024)

Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
por: Xu, Shaoyang, et al.
Publicado: (2024)

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
por: Sun, Haoran, et al.
Publicado: (2024)

DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs
por: Meng, Zijie, et al.
Publicado: (2024)

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
por: Liang, Xiao, et al.
Publicado: (2026)

Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration
por: Xiao, Sibo, et al.
Publicado: (2025)

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding
por: Luo, Xiangzhong, et al.
Publicado: (2026)

Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons
por: Leng, Yongqi, et al.
Publicado: (2024)

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
por: Xiong, Jing, et al.
Publicado: (2025)

Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classification
por: Langner, Mikołaj, et al.
Publicado: (2025)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
por: Wu, Wei, et al.
Publicado: (2024)

Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
por: Ji, Deyi, et al.
Publicado: (2024)

Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework
por: Zheng, Quan, et al.
Publicado: (2026)

DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
por: Zheng, Chuanyang, et al.
Publicado: (2024)

Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
por: Chen, Kunfeng, et al.
Publicado: (2026)

Context-aware Biases for Length Extrapolation
por: Veisi, Ali, et al.
Publicado: (2025)

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
por: Yang, Lei, et al.
Publicado: (2026)

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
por: Xu, Zhen, et al.
Publicado: (2025)

Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding
por: Zhao, Liang, et al.
Publicado: (2023)

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
por: Mao, Yanxu, et al.
Publicado: (2024)

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation
por: Zheng, Shunfan, et al.
Publicado: (2025)

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms
por: Li, Kewei, et al.
Publicado: (2025)

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
por: Lu, Yi, et al.
Publicado: (2025)

SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization
por: Vijayaraghavan, Prashanth, et al.
Publicado: (2026)

Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
por: Chen, Jingchang, et al.
Publicado: (2024)

Divide-or-Conquer? Which Part Should You Distill Your LLM?
por: Wu, Zhuofeng, et al.
Publicado: (2024)

Intrinsic Entropy of Context Length Scaling in LLMs
por: Shi, Jingzhe, et al.
Publicado: (2025)

From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers
por: Duan, Shaoxiong, et al.
Publicado: (2023)

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
por: Zheng, Chuanyang, et al.
Publicado: (2024)

An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
por: Zhang, Yizhou, et al.
Publicado: (2024)

CLEX: Continuous Length Extrapolation for Large Language Models
por: Chen, Guanzheng, et al.
Publicado: (2023)