{"total":114,"rows":[{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455,"area":null},{"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":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303,"area":null},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233,"area":null},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202,"area":null},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186,"area":null},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","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":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119,"area":null},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84,"area":null},{"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":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"area":null},{"id":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69,"area":null},{"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":"2506.12103","title":"The Amazon Nova Family of Models: Technical Report and Model Card","created":"2025-03-17","cited_by_count":41,"area":null},{"id":"2511.02817","title":"Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities","created":"2025-11-04","cited_by_count":40,"area":null},{"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":"2406.14673","title":"Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2406.06025","title":"RepoQA: Evaluating Long Context Code Understanding","created":"2024-06-10","cited_by_count":35,"area":null},{"id":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"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":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2404.10308","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","created":"2024-04-16","cited_by_count":30,"area":null},{"id":"2402.14116","title":"FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models","created":"2024-02-21","cited_by_count":29,"area":null},{"id":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2410.04199","title":"LongGenBench: Long-context Generation Benchmark","created":"2024-10-05","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":"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":"2502.19512","title":"TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs","created":"2025-02-26","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":"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":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"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":"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":"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":"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":"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":"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":"2503.08640","title":"Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2402.13551","title":"Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2407.07799","title":"Attribute or Abstain: Large Language Models as Long Document Assistants","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2404.03561","title":"Select and Summarize: Scene Saliency for Movie Script Summarization","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2408.10151","title":"Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models","created":"2024-08-19","cited_by_count":9,"area":null},{"id":"2502.00977","title":"Context-Aware Hierarchical Merging for Long Document Summarization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2504.04713","title":"Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2506.11440","title":"AbsenceBench: Language Models Can't Tell What's Missing","created":"2025-06-13","cited_by_count":9,"area":null},{"id":"2508.07479","title":"Positional Biases Shift as Inputs Approach Context Window Limits","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2404.16297","title":"When Fuzzing Meets LLMs: Challenges and Opportunities","created":"2024-04-25","cited_by_count":8,"area":null},{"id":"2405.02842","title":"IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs","created":"2024-05-05","cited_by_count":8,"area":null},{"id":"2406.16086","title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2510.22548","title":"LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?","created":"2025-10-26","cited_by_count":8,"area":null},{"id":"2408.14906","title":"Writing in the Margins: Better Inference Pattern for Long Context Retrieval","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2312.08618","title":"Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2406.17588","title":"LongIns: A Challenging Long-context Instruction-based Exam for LLMs","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2412.15386","title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2505.23295","title":"How Does Response Length Affect Long-Form Factuality","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2601.12906","title":"Gated Differentiable Working Memory for Long-Context Language Modeling","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2406.10786","title":"Evaluating LLMs with Multiple Problems at once","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2502.14409","title":"Unstructured Evidence Attribution for Long Context Query Focused Summarization","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2506.01872","title":"Is Extending Modality The Right Path Towards Omni-Modality?","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2505.16518","title":"CUB: Benchmarking Context Utilisation Techniques for Language Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2510.17725","title":"AcademicEval: Live Long-Context LLM Benchmark","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2605.10544","title":"Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2409.06338","title":"Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Tasks","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2411.15993","title":"Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2505.13353","title":"Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2603.22608","title":"Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2605.28079","title":"ATLAS: All-round Testing of Long-context Abilities across Scales","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2406.11238","title":"What Kinds of Tokens Benefit from Distant Text? An Analysis on Long Context Language Modeling","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2406.13632","title":"DoubleDipper: Improving Long-Context LLMs via Context Recycling","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2408.02439","title":"Long Input Benchmark for Russian Analysis","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2503.04355","title":"Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2512.17179","title":"Enhancing Long Document Long Form Summarisation with Self-Planning","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2606.04646","title":"QO-Bench: Diagnosing Query-Operator-Preserving Retrieval over Typed Event Tuples","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2607.09415","title":"Self-Guided Test-Time Training for Long-Context LLMs","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2410.01637","title":"On The Adaptation of Unlimiformer for Decoder-Only Transformers","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2506.04907","title":"Context Is Not Comprehension","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2507.01853","title":"Eka-Eval: An Evaluation Framework for Low-Resource Multilingual Large Language Models","created":"2025-07-02","cited_by_count":0,"area":null}],"next_cursor":"100"}