{"total":58,"rows":[{"id":"2510.05381","title":"Context Length Alone Hurts LLM Performance Despite Perfect Retrieval","created":"2025-10-06","cited_by_count":127,"area":null},{"id":"2502.05167","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","created":"2025-02-07","cited_by_count":126,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"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":"2505.07897","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","created":"2025-05-12","cited_by_count":37,"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":"2505.20099","title":"Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities","created":"2025-05-26","cited_by_count":31,"area":null},{"id":"2410.22394","title":"AAAR-1.0: Assessing AI's Potential to Assist Research","created":"2024-10-29","cited_by_count":24,"area":null},{"id":"2505.19457","title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","created":"2025-05-26","cited_by_count":22,"area":null},{"id":"2502.12982","title":"Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","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":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11,"area":null},{"id":"2505.16483","title":"Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning","created":"2025-05-22","cited_by_count":11,"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":"2502.16684","title":"WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2502.16860","title":"LongAttn: Selecting Long-context Training Data via Token-level Attention","created":"2025-02-24","cited_by_count":9,"area":null},{"id":"2502.20730","title":"DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking","created":"2025-02-28","cited_by_count":9,"area":null},{"id":"2503.03588","title":"PowerAttention: Exponentially Scaling of Receptive Fields for Effective Sparse Attention","created":"2025-03-05","cited_by_count":9,"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":"2412.04905","title":"DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2505.10063","title":"CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability","created":"2025-05-15","cited_by_count":4,"area":null},{"id":"2510.18413","title":"Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference","created":"2025-10-21","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":"2504.17366","title":"LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2506.02510","title":"M$^3$FinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.16440","title":"Evaluating the Use of LLMs for Documentation to Code Traceability","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2507.09506","title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2509.21732","title":"How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2604.22294","title":"SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.31086","title":"Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2505.20195","title":"Monocle: Hybrid Local-Global In-Context Evaluation for Long-Text Generation with Uncertainty-Based Active Learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.01185","title":"Modular Techniques for Synthetic Long-Context Data Generation in Language Model Training and Evaluation","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2605.30628","title":"The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2411.10145","title":"An Effective Framework to Help Large Language Models Handle Numeric-involved Long-context Tasks","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2412.09884","title":"Benchmarking Table Comprehension In The Wild","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2501.02772","title":"GeAR: Generation Augmented Retrieval","created":"2025-01-06","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":"2507.16271","title":"Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2508.18093","title":"Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.16783","title":"LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2602.19543","title":"Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.06416","title":"Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.19685","title":"An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.10235","title":"Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.24194","title":"Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.09328","title":"WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.04405","title":"Training-Free Hashing-Based Attention via Binary Principal Components","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.20844","title":"Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.27173","title":"Realize What Matters: Principled Context Representation for Large-Scale Reasoning","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27279","title":"EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27925","title":"Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}