{"total":233,"rows":[{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"id":"2404.06654","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","created":"2024-04-09","cited_by_count":1346,"area":null},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880,"area":"inference"},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379,"area":"lr"},{"id":"2402.13718","title":"$\\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens","created":"2024-02-21","cited_by_count":367,"area":null},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202,"area":null},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186,"area":null},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152,"area":"lr"},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148,"area":null},{"id":"2405.12532","title":"PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference","created":"2024-05-21","cited_by_count":147,"area":"inference"},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143,"area":"mechinterp"},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136,"area":null},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125,"area":null},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2406.17419","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","created":"2024-06-25","cited_by_count":122,"area":null},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119,"area":null},{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119,"area":"rag"},{"id":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112,"area":"inference"},{"id":"2401.18058","title":"LongAlign: A Recipe for Long Context Alignment of Large Language Models","created":"2024-01-31","cited_by_count":106,"area":"alignment"},{"id":"2408.09559","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","created":"2024-08-18","cited_by_count":106,"area":"lr"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2506.21605","title":"MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents","created":"2025-06-20","cited_by_count":84,"area":"agents"},{"id":"2602.16313","title":"MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks","created":"2026-02-18","cited_by_count":84,"area":"agents"},{"id":"2402.05136","title":"LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K","created":"2024-02-06","cited_by_count":81,"area":null},{"id":"2406.16264","title":"One Thousand and One Pairs: A \"novel\" challenge for long-context language models","created":"2024-06-24","cited_by_count":80,"area":null},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73,"area":"inference"},{"id":"2407.08683","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","created":"2024-07-11","cited_by_count":73,"area":null},{"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":"2309.09150","title":"Can Large Language Models Understand Real-World Complex Instructions?","created":"2023-09-17","cited_by_count":69,"area":null},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64,"area":"rag"},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63,"area":null},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2402.17463","title":"Training-Free Long-Context Scaling of Large Language Models","created":"2024-02-27","cited_by_count":62,"area":null},{"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":"2309.13345","title":"BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2409.02076","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","created":"2024-09-03","cited_by_count":47,"area":null},{"id":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41,"area":"rag"},{"id":"2402.10790","title":"In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss","created":"2024-02-16","cited_by_count":36,"area":null},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2411.07037","title":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios","created":"2024-11-11","cited_by_count":33,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"id":"2404.06480","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","created":"2024-04-09","cited_by_count":32,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","cited_by_count":28,"area":null},{"id":"2503.13517","title":"CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning","created":"2025-03-14","cited_by_count":28,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2403.00071","title":"Resonance RoPE: Improving Context Length Generalization of Large Language Models","created":"2024-02-29","cited_by_count":27,"area":null},{"id":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","cited_by_count":27,"area":null},{"id":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2408.03246","title":"Making Long-Context Language Models Better Multi-Hop Reasoners","created":"2024-08-06","cited_by_count":26,"area":"lr"},{"id":"2503.11751","title":"reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs","created":"2025-03-14","cited_by_count":25,"area":"alignment"},{"id":"2401.15042","title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models","created":"2024-01-26","cited_by_count":24,"area":null},{"id":"2406.02472","title":"Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding","created":"2024-06-04","cited_by_count":23,"area":null},{"id":"2405.03939","title":"Long Context Alignment with Short Instructions and Synthesized Positions","created":"2024-05-07","cited_by_count":22,"area":null},{"id":"2409.02465","title":"DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels","created":"2024-09-04","cited_by_count":21,"area":"lr"},{"id":"2409.20222","title":"Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models","created":"2024-09-30","cited_by_count":20,"area":null},{"id":"2506.13356","title":"StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns","created":"2025-06-16","cited_by_count":20,"area":null},{"id":"2603.01045","title":"Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2503.01996","title":"One ruler to measure them all: Benchmarking multilingual long-context language models","created":"2025-03-03","cited_by_count":19,"area":null},{"id":"2507.14675","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","created":"2025-07-19","cited_by_count":19,"area":"mllm"},{"id":"2601.02872","title":"LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark","created":"2026-01-06","cited_by_count":19,"area":null},{"id":"2310.15147","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2406.19292","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","created":"2024-06-27","cited_by_count":18,"area":"lr"},{"id":"2504.05370","title":"EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design","created":"2025-04-07","cited_by_count":18,"area":"agents"},{"id":"2403.11802","title":"Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models","created":"2024-03-18","cited_by_count":17,"area":null},{"id":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17,"area":null},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2410.01671","title":"Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2410.14641","title":"Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs","created":"2024-10-18","cited_by_count":16,"area":null},{"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":"2502.18993","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","created":"2025-02-26","cited_by_count":16,"area":"rag"},{"id":"2508.15658","title":"SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation","created":"2025-08-21","cited_by_count":16,"area":null},{"id":"2310.19240","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2403.03514","title":"CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models","created":"2024-03-06","cited_by_count":15,"area":null},{"id":"2405.06683","title":"ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization","created":"2024-05-06","cited_by_count":15,"area":"rag"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2503.04723","title":"Shifting Long-Context LLMs Research from Input to Output","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2406.09897","title":"3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding","created":"2024-06-14","cited_by_count":13,"area":null},{"id":"2406.15019","title":"MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens","created":"2024-06-21","cited_by_count":13,"area":null},{"id":"2407.15176","title":"ReAttention: Training-Free Infinite Context with Finite Attention Scope","created":"2024-07-21","cited_by_count":13,"area":null},{"id":"2408.15496","title":"ReMamba: Equip Mamba with Effective Long-Sequence Modeling","created":"2024-08-28","cited_by_count":13,"area":"ssm"},{"id":"2409.17264","title":"No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2410.04727","title":"Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2410.16848","title":"ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage","created":"2024-10-22","cited_by_count":12,"area":null},{"id":"2411.05000","title":"Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2509.21361","title":"Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs","created":"2025-09-21","cited_by_count":12,"area":null}],"next_cursor":"100"}