# Extending Context Window of Large Language Models via Semantic Compression

arXiv: https://arxiv.org/abs/2312.09571 · HTML: https://mlsanity.com/paper/2312.09571/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 30 of 30)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [Landmark Attention: Random-Access Infinite Context Length for Transformers](https://mlsanity.com/paper/2305.16300/) (2023)
- [Exploring Length Generalization in Large Language Models](https://mlsanity.com/paper/2207.04901/) (2022)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text](https://mlsanity.com/paper/2305.13304/) (2023)
- [Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2311.12351/) (2023)
- [Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering](https://mlsanity.com/paper/2304.12102/) (2023)
- [Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks](https://mlsanity.com/paper/2310.13800/) (2023)
- [Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2109.08925/) (2021)
- [Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport](https://mlsanity.com/paper/2305.04034/) (2023)
- [EFOk-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation](https://mlsanity.com/paper/2307.13701/) (2023)

## Built on by (most cited first, 30 of 45)

- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2502.00299/) (2025)
- [DeciMamba: Exploring the Length Extrapolation Potential of Mamba](https://mlsanity.com/paper/2406.14528/) (2024)
- [Efficient Prompting Methods for Large Language Models: A Survey](https://mlsanity.com/paper/2404.01077/) (2024)
- [Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models](https://mlsanity.com/paper/2407.06089/) (2024)
- [Agentic Software Engineering: Foundational Pillars and a Research Roadmap](https://mlsanity.com/paper/2509.06216/) (2025)
- [Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example](https://mlsanity.com/paper/2408.06318/) (2024)
- [U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack](https://mlsanity.com/paper/2503.00353/) (2025)
- [Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw](https://mlsanity.com/paper/2603.12644/) (2026)
- [Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression](https://mlsanity.com/paper/2502.01941/) (2025)
- [An LLM-Tool Compiler for Fused Parallel Function Calling](https://mlsanity.com/paper/2405.17438/) (2024)
- [Understanding and Improving Information Preservation in Prompt Compression for LLMs](https://mlsanity.com/paper/2503.19114/) (2025)
- [ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents](https://mlsanity.com/paper/2511.12960/) (2025)
- [Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory](https://mlsanity.com/paper/2405.08707/) (2024)
- [Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference](https://mlsanity.com/paper/2501.12959/) (2025)
- [You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL](https://mlsanity.com/paper/2409.12172/) (2024)
- [Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding](https://mlsanity.com/paper/2406.12331/) (2024)
- [Reducing Distraction in Long-Context Language Models by Focused Learning](https://mlsanity.com/paper/2411.05928/) (2024)
- [Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference](https://mlsanity.com/paper/2604.02985/) (2026)
- [SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models](https://mlsanity.com/paper/2506.15695/) (2025)
- [Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models](https://mlsanity.com/paper/2410.15116/) (2024)
- [Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents](https://mlsanity.com/paper/2601.14287/) (2026)
- [Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2409.13385/) (2024)
- [Quantifying Positional Biases in Text Embedding Models](https://mlsanity.com/paper/2412.15241/) (2024)
- [PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression](https://mlsanity.com/paper/2504.16574/) (2025)
- [Variable-Length Semantic IDs for Recommender Systems](https://mlsanity.com/paper/2602.16375/) (2026)
- [Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge](https://mlsanity.com/paper/2511.00505/) (2025)
- [ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models](https://mlsanity.com/paper/2606.11164/) (2026)

## Abstract (arXiv)

Transformer-based Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. This constraint restricts their applicability in scenarios involving long texts. We propose a novel semantic compression method that enables generalization to texts that are 6-8 times longer, without incurring significant computational costs or requiring fine-tuning. Our proposed framework draws inspiration from source coding in information theory and employs a pre-trained model to reduce the semantic redundancy of long inputs before passing them to the LLMs for downstream tasks. Experimental results demonstrate that our method effectively extends the context window of LLMs across a range of tasks including question answering, summarization, few-shot learning, and information retrieval. Furthermore, the proposed semantic compression method exhibits consistent fluency in text generation while reducing the associated computational overhead.