Image de couverture de livre

Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Gu, Shangding
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
par: Liu, Xianyang, et autres
Publié: (2026)

Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime
par: Wang, Yuqing, et autres
Publié: (2025)

LLMs Should Express Uncertainty Explicitly
par: Guo, Junyu, et autres
Publié: (2026)

Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
par: Yang, Yingxuan, et autres
Publié: (2026)

A Review of Safe Reinforcement Learning: Methods, Theory and Applications
par: Gu, Shangding, et autres
Publié: (2022)

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
par: Gu, Shangding, et autres
Publié: (2024)

Overflow Prevention Enhances Long-Context Recurrent LLMs
par: Ben-Kish, Assaf, et autres
Publié: (2025)

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
par: Gu, Shangding, et autres
Publié: (2024)

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
par: Song, Woomin, et autres
Publié: (2024)

StyleBench: Evaluating thinking styles in Large Language Models
par: Guo, Junyu, et autres
Publié: (2025)

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
par: Xu, Peng, et autres
Publié: (2024)

LongSafety: Enhance Safety for Long-Context LLMs
par: Huang, Mianqiu, et autres
Publié: (2024)

Training Long-Context LLMs Efficiently via Chunk-wise Optimization
par: Li, Wenhao, et autres
Publié: (2025)

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
par: Karten, Seth, et autres
Publié: (2026)

Privacy Reasoning in Ambiguous Contexts
par: Yi, Ren, et autres
Publié: (2025)

Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
par: Zhu, Kan, et autres
Publié: (2025)

Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs
par: Ni, Wentao, et autres
Publié: (2026)

The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
par: Roy, Amartya, et autres
Publié: (2026)

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
par: Goren, Shani, et autres
Publié: (2026)

Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
par: Dietz, Florian, et autres
Publié: (2026)

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling
par: Kang, Shijia, et autres
Publié: (2025)

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
par: Gu, Shangding, et autres
Publié: (2025)

Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models
par: Qian, Tangwen, et autres
Publié: (2024)

Graph Federated Learning for Personalized Privacy Recommendation
par: Na, Ce, et autres
Publié: (2025)

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
par: Gu, Zhuohan, et autres
Publié: (2026)

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
par: Jin, Bowen, et autres
Publié: (2024)

Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
par: Huang, Xingyue, et autres
Publié: (2025)

Scaling Limits of Long-Context Transformers
par: Bruno, Giuseppe, et autres
Publié: (2026)

TracLLM: A Generic Framework for Attributing Long Context LLMs
par: Wang, Yanting, et autres
Publié: (2025)

LIMR: Less is More for RL Scaling
par: Li, Xuefeng, et autres
Publié: (2025)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
par: Xiao, Chaojun, et autres
Publié: (2024)

SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
par: Lee, Changhun, et autres
Publié: (2025)

MoBA: Mixture of Block Attention for Long-Context LLMs
par: Lu, Enzhe, et autres
Publié: (2025)

A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation
par: Li, Zhiwei, et autres
Publié: (2025)

Q-ROAR: Outlier-Aware Rescaling for RoPE Position Interpolation in Quantized Long-Context LLMs
par: Qiao, Ye, et autres
Publié: (2025)

Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
par: Xu, Hongtao, et autres
Publié: (2025)

Compute-Optimal LLMs Provably Generalize Better With Scale
par: Finzi, Marc, et autres
Publié: (2025)

MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMs
par: Zhao, Chenchen, et autres
Publié: (2025)

Long Context In-Context Compression by Getting to the Gist of Gisting
par: Petrov, Aleksandar, et autres
Publié: (2025)

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
par: Hu, Junhao, et autres
Publié: (2026)