Imagen de Portada

From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Yiqing, Lei, Yu, Si, Shuzheng, Sun, Qingyan, Wang, Wei, Wu, Yifei, Wen, Hao, Chen, Gang, Qi, Fanchao, Sun, Maosong
Formato:	Preprint
Publicado:	2025
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

RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
por: Lei, Yu, et al.
Publicado: (2025)

From Context to Skills: Can Language Models Learn from Context Skillfully?
por: Si, Shuzheng, et al.
Publicado: (2026)

GATEAU: Selecting Influential Samples for Long Context Alignment
por: Si, Shuzheng, et al.
Publicado: (2024)

FaithLens: Detecting and Explaining Faithfulness Hallucination
por: Si, Shuzheng, et al.
Publicado: (2025)

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
por: Si, Shuzheng, et al.
Publicado: (2025)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
por: Bai, Yuzhuo, et al.
Publicado: (2026)

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
por: Wang, Ran, et al.
Publicado: (2025)

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
por: Si, Shuzheng, et al.
Publicado: (2025)

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
por: Huang, Yuxiang, et al.
Publicado: (2025)

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
por: Si, Shuzheng, et al.
Publicado: (2025)

Context-DPO: Aligning Language Models for Context-Faithfulness
por: Bi, Baolong, et al.
Publicado: (2024)

DeepSeek-OCR: Contexts Optical Compression
por: Wei, Haoran, et al.
Publicado: (2025)

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
por: Zhao, Haozhe, et al.
Publicado: (2024)

In-context Autoencoder for Context Compression in a Large Language Model
por: Ge, Tao, et al.
Publicado: (2023)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
por: Ming, Yifei, et al.
Publicado: (2024)

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
por: Ju, Li, et al.
Publicado: (2026)

Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
por: Huang, Chensen, et al.
Publicado: (2024)

Variational Uncertainty Decomposition for In-Context Learning
por: Jayasekera, I. Shavindra, et al.
Publicado: (2025)

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
por: An, Kaikai, et al.
Publicado: (2024)

Context-Aware Decoding for Faithful Vision-Language Generation
por: Fazli, Mehrdad, et al.
Publicado: (2026)

Submodular Context Partitioning and Compression for In-Context Learning
por: Zheng, Shaoyi, et al.
Publicado: (2025)

Reinforcement Learning Approach for Integrating Compressed Contexts into Knowledge Graphs
por: Quach, Ngoc, et al.
Publicado: (2024)

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

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
por: Xiao, Chaojun, et al.
Publicado: (2024)

Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
por: Liu, Zhenghao, et al.
Publicado: (2025)

Discovering Elementary Discourse Units in Textual Data Using Canonical Correlation Analysis
por: Mehndiratta, Akanksha, et al.
Publicado: (2024)

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
por: Li, Yuepei, et al.
Publicado: (2024)

On the Role of Context for Discourse Relation Classification in Scientific Writing
por: Wan, Stephen, et al.
Publicado: (2025)

From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
por: Zhou, Yitian, et al.
Publicado: (2026)

From Compression to Expression: A Layerwise Analysis of In-Context Learning
por: Jiang, Jiachen, et al.
Publicado: (2025)

Context Forcing: Consistent Autoregressive Video Generation with Long Context
por: Chen, Shuo, et al.
Publicado: (2026)

CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
por: Tan, Zhehao, et al.
Publicado: (2026)

Hodge Decomposition for Urban Traffic Flow: Limits on Dense OD Graphs and Advantages on Road Networks - Los Angeles Case
por: Sun, Yifei
Publicado: (2025)

Context-Efficient Retrieval with Factual Decomposition
por: Li, Yanhong, et al.
Publicado: (2025)

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
por: Yang, Cehao, et al.
Publicado: (2025)

Effective In-Context Example Selection through Data Compression
por: Sun, Zhongxiang, et al.
Publicado: (2024)

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
por: Zhao, Haozhe, et al.
Publicado: (2026)

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
por: Zhao, Haozhe, et al.
Publicado: (2023)

Finite-time stabilization of discontinuous fuzzy inertial Cohen–Grossberg neural networks with mixed time-varying delays.
por: Fanchao Kong
Publicado: (2021)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
por: Zhang, Qinggang, et al.
Publicado: (2025)