{"total":97,"rows":[{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390,"area":null},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356,"area":null},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287,"area":null},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256,"area":"rag"},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249,"area":"lr"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2307.06945","title":"In-context Autoencoder for Context Compression in a Large Language Model","created":"2023-07-13","cited_by_count":199,"area":"inference"},{"id":"2305.18323","title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","created":"2023-05-23","cited_by_count":184,"area":"lr"},{"id":"2401.06201","title":"EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction","created":"2024-01-11","cited_by_count":154,"area":"agents"},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119,"area":"lr"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2410.12388","title":"Prompt Compression for Large Language Models: A Survey","created":"2024-10-16","cited_by_count":67,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2402.18700","title":"Learning to Compress Prompt in Natural Language Formats","created":"2024-02-28","cited_by_count":55,"area":null},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50,"area":"inference"},{"id":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2408.03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","created":"2024-08-06","cited_by_count":47,"area":"inference"},{"id":"2312.09571","title":"Extending Context Window of Large Language Models via Semantic Compression","created":"2023-12-15","cited_by_count":45,"area":null},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2308.08758","title":"Discrete Prompt Compression with Reinforcement Learning","created":"2023-08-17","cited_by_count":42,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"id":"2509.06216","title":"Agentic Software Engineering: Foundational Pillars and a Research Roadmap","created":"2025-09-07","cited_by_count":41,"area":"agents"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2403.04317","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30,"area":"rag"},{"id":"2312.08901","title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","created":"2023-12-14","cited_by_count":26,"area":"lr"},{"id":"2310.02409","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","created":"2023-10-03","cited_by_count":23,"area":null},{"id":"2510.05069","title":"SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs","created":"2025-10-06","cited_by_count":22,"area":"lr"},{"id":"2502.00791","title":"Vision-centric Token Compression in Large Language Model","created":"2025-02-02","cited_by_count":21,"area":"inference"},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"id":"2407.15504","title":"Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models","created":"2024-07-22","cited_by_count":19,"area":"inference"},{"id":"2404.00489","title":"Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression","created":"2024-03-30","cited_by_count":18,"area":"inference"},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2504.01707","title":"InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation","created":"2025-04-02","cited_by_count":17,"area":null},{"id":"2405.03085","title":"Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation","created":"2024-05-06","cited_by_count":16,"area":"rag"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2503.19114","title":"Understanding and Improving Information Preservation in Prompt Compression for LLMs","created":"2025-03-24","cited_by_count":15,"area":"inference"},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2407.02211","title":"PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning","created":"2024-07-02","cited_by_count":13,"area":null},{"id":"2504.08934","title":"Long Context In-Context Compression by Getting to the Gist of Gisting","created":"2025-04-11","cited_by_count":13,"area":"inference"},{"id":"2602.21221","title":"Latent Context Compilation: Distilling Long Context into Compact Portable Memory","created":"2026-01-31","cited_by_count":13,"area":null},{"id":"2406.13618","title":"In-Context Former: Lightning-fast Compressing Context for Large Language Model","created":"2024-06-19","cited_by_count":12,"area":null},{"id":"2501.12959","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","created":"2025-01-22","cited_by_count":12,"area":"inference"},{"id":"2308.07326","title":"AI Text-to-Behavior: A Study In Steerability","created":"2023-08-07","cited_by_count":11,"area":null},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2508.05282","title":"Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning","created":"2025-08-07","cited_by_count":11,"area":"lr"},{"id":"2310.13682","title":"Optimizing Retrieval-augmented Reader Models via Token Elimination","created":"2023-10-20","cited_by_count":10,"area":"rag"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"area":"alignment"},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2410.11786","title":"Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability","created":"2024-10-15","cited_by_count":9,"area":"inference"},{"id":"2410.14042","title":"Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles","created":"2024-10-17","cited_by_count":9,"area":"inference"},{"id":"2304.11220","title":"Learn What NOT to Learn: Towards Generative Safety in Chatbots","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2406.06110","title":"Recurrent Context Compression: Efficiently Expanding the Context Window of LLM","created":"2024-06-10","cited_by_count":8,"area":"inference"},{"id":"2507.22931","title":"Enhancing RAG Efficiency with Adaptive Context Compression","created":"2025-07-24","cited_by_count":8,"area":"rag"},{"id":"2505.15774","title":"Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention","created":"2025-05-21","cited_by_count":7,"area":"inference"},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2507.11942","title":"DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression","created":"2025-07-16","cited_by_count":7,"area":"inference"},{"id":"2405.17062","title":"UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation","created":"2024-05-27","cited_by_count":6,"area":"lr"},{"id":"2504.11004","title":"Dynamic Compressing Prompts for Efficient Inference of Large Language Models","created":"2025-04-15","cited_by_count":6,"area":"inference"},{"id":"2506.15001","title":"Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2409.13385","title":"Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2024-09-20","cited_by_count":5,"area":"rag"},{"id":"2503.07956","title":"EFPC: Towards Efficient and Flexible Prompt Compression","created":"2025-03-11","cited_by_count":5,"area":"inference"},{"id":"2506.01084","title":"zip2zip: Inference-Time Adaptive Tokenization via Online Compression","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2406.07588","title":"AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning","created":"2024-06-11","cited_by_count":4,"area":"mllm"},{"id":"2501.06730","title":"Better Prompt Compression Without Multi-Layer Perceptrons","created":"2025-01-12","cited_by_count":4,"area":"inference"},{"id":"2504.16574","title":"PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression","created":"2025-04-23","cited_by_count":4,"area":"inference"},{"id":"2311.03253","title":"Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2405.11299","title":"The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving","created":"2024-05-18","cited_by_count":3,"area":"inference"},{"id":"2511.17129","title":"Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2602.17046","title":"Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs","created":"2025-12-01","cited_by_count":3,"area":"agents"},{"id":"2603.19733","title":"PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction","created":"2026-03-20","cited_by_count":3,"area":"inference"},{"id":"2408.00167","title":"Finch: Prompt-guided Key-Value Cache Compression","created":"2024-07-31","cited_by_count":2,"area":"rag"},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2508.08446","title":"OverFill: Two-Stage Models for Efficient Language Model Decoding","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.09474","title":"Multimodal Policy Internalization for Conversational Agents","created":"2025-10-10","cited_by_count":2,"area":"agents"},{"id":"2602.03784","title":"Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2602.15843","title":"The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2407.19410","title":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","created":"2024-07-28","cited_by_count":1,"area":"inference"},{"id":"2503.08159","title":"Mimicking How Humans Interpret Out-of-Context Sentences Through Controlled Toxicity Decoding","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2505.22907","title":"Conversational Alignment with Artificial Intelligence in Context","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.21394","title":"AI Compute Architecture and Evolution Trends","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2603.09222","title":"EnComp: Lightweight Encoder-Only Context Compression for Retrieval-Augmented Question Answering","created":"2026-03-10","cited_by_count":1,"area":"rag"},{"id":"2603.23525","title":"Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial","created":"2026-03-06","cited_by_count":1,"area":"inference"},{"id":"2604.06627","title":"DiffuMask: Diffusion Language Model for Token-level Prompt Pruning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"},{"id":"2406.18173","title":"UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2510.10224","title":"Text2Token: Unsupervised Text Representation Learning with Token Target Prediction","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.22963","title":"When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents","created":"2025-10-27","cited_by_count":0,"area":"agents"},{"id":"2604.14403","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","created":"2026-04-15","cited_by_count":0,"area":"rag"},{"id":"2604.22565","title":"Learning Evidence Highlighting for Frozen LLMs","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.12411","title":"Context-Driven Incremental Compression for Multi-Turn Dialogue Generation","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.05152","title":"Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2610.13605","title":"zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss","created":"2026-10-09","cited_by_count":0,"area":"inference"}],"next_cursor":null}