BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models

arXiv:2511.04919 · cs.CL, cs.AI · Submitted 2025-11-07 · Read on arXiv

cs.CL, cs.AI

Submitted: 2025-11-07

Updated: 2026-09-20

Comments: 11 pages, 3 figures, 5 tables. Evaluated on 700 QA pairs across multiple document lengths

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 18× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• RAG — 7× in this paper · explained in 3 episodes
• Pruning — 6× in this paper · explained in 4 episodes
• F1 Score — 5× in this paper · explained in 3 episodes
• Perplexity — 5× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Longformer: The Long-Document Transformer
• GPT-4 Technical Report
• The Llama 3 Herd of Models
• Generating Long Sequences with Sparse Transformers
• Compressive Transformers for Long-Range Sequence Modelling
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• LLaMA: Open and Efficient Foundation Language Models
• Extending Context Window of Large Language Models via Positional Interpolation
• REPLUG: Retrieval-Augmented Black-Box Language Models
• Adapting Language Models to Compress Contexts
• Atlas: Few-shot Learning with Retrieval Augmented Language Models
• LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
• LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
• MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
• MemLong: Memory-Augmented Retrieval for Long Text Modeling
• InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
• Memory Networks
• Neural Turing Machines
• Compressing Context to Enhance Inference Efficiency of Large Language Models
• RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering