Image de couverture de livre

Less Is More: Elevating RAG via Performance-Driven Context Compression

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cui, Ziqiang, Weng, Yunpeng, Tang, Xing, Liu, Peiyang, Li, Shiwei, He, Bowei, Chen, Jiamin, Zhang, Yansen, He, Xiuqiang, Ma, Chen
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
par: Cui, Ziqiang, et autres
Publié: (2025)

Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketing
par: He, Bowei, et autres
Publié: (2024)

Comprehending Knowledge Graphs with Large Language Models for Recommender Systems
par: Cui, Ziqiang, et autres
Publié: (2024)

Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networks
par: Cui, Ziqiang, et autres
Publié: (2024)

Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
par: Liu, Peiyang, et autres
Publié: (2025)

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
par: Li, Shiwei, et autres
Publié: (2025)

Beyong Tokens: Item-aware Attention for LLM-based Recommendation
par: Zhang, Xiaokun, et autres
Publié: (2026)

Expected Transaction Value Optimization for Precise Marketing in FinTech Platforms
par: Weng, Yunpeng, et autres
Publié: (2024)

Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA
par: Tang, Xing, et autres
Publié: (2026)

Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
par: Liu, Shuqi, et autres
Publié: (2025)

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity
par: Li, Shiwei, et autres
Publié: (2025)

A Predict-Then-Optimize Customer Allocation Framework for Online Fund Recommendation
par: Tang, Xing, et autres
Publié: (2025)

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
par: Zhang, Xing, et autres
Publié: (2026)

FrugalRAG: Less is More in RL Finetuning for Multi-Hop Question Answering
par: Java, Abhinav, et autres
Publié: (2025)

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
par: Tan, Chenchen, et autres
Publié: (2026)

Less LLM, More Documents: Searching for Improved RAG
par: Ning, Jingjie, et autres
Publié: (2025)

StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
par: Chen, Zhirui, et autres
Publié: (2026)

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
par: Li, Yulin, et autres
Publié: (2025)

In-Context Former: Lightning-fast Compressing Context for Large Language Model
par: Wang, Xiangfeng, et autres
Publié: (2024)

LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation
par: Yuan, Jiahao, et autres
Publié: (2025)

From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement
par: Yan, Jianzhi, et autres
Publié: (2025)

Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
par: Zhuang, Xialie, et autres
Publié: (2025)

Less Context, Same Performance: A RAG Framework for Resource-Efficient LLM-Based Clinical NLP
par: Cheetirala, Satya Narayana, et autres
Publié: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
par: Deng, Xun, et autres
Publié: (2025)

End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift Modeling
par: Sun, Zexu, et autres
Publié: (2024)

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
par: Zhou, Jiawei, et autres
Publié: (2025)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
par: Li, Xinze, et autres
Publié: (2024)

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
par: Zhao, Runsong, et autres
Publié: (2026)

Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection
par: Song, Zhipeng, et autres
Publié: (2026)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
par: Jeong, Yeonseok, et autres
Publié: (2025)

Enhancing RAG Efficiency with Adaptive Context Compression
par: Guo, Shuyu, et autres
Publié: (2025)

Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven
par: Tang, Jiwei, et autres
Publié: (2026)

Less is More: Adaptive Program Repair with Bug Localization and Preference Learning
par: Dai, Zhenlong, et autres
Publié: (2025)

SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?
par: Chen, Jiamin, et autres
Publié: (2026)

Shapley Value-driven Data Pruning for Recommender Systems
par: Zhang, Yansen, et autres
Publié: (2025)

ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
par: He, Liyang, et autres
Publié: (2025)

Creative and Context-Aware Translation of East Asian Idioms with GPT-4
par: Tang, Kenan, et autres
Publié: (2024)

98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router
par: Liu, Xunzhuo, et autres
Publié: (2026)

Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
par: Liu, Peiyang, et autres
Publié: (2026)

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
par: Liu, Peiyang, et autres
Publié: (2026)