{"total":72,"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":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63,"area":null},{"id":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"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":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","cited_by_count":31,"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":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17,"area":null},{"id":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","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":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2508.15709","title":"Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation","created":"2025-08-21","cited_by_count":9,"area":"distill"},{"id":"2510.10276","title":"Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs","created":"2025-10-11","cited_by_count":9,"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":"2406.17095","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2506.07334","title":"Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models","created":"2025-06-09","cited_by_count":6,"area":"inference"},{"id":"2505.16134","title":"Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2601.02993","title":"Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation","created":"2026-01-06","cited_by_count":5,"area":"rag"},{"id":"2602.16837","title":"A Structural Theory of Position Bias in Transformers","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2406.04046","title":"ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints","created":"2024-06-06","cited_by_count":4,"area":"lr"},{"id":"2406.12018","title":"CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2412.15241","title":"Quantifying Positional Biases in Text Embedding Models","created":"2024-12-13","cited_by_count":4,"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":"2602.01405","title":"Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents","created":"2026-02-01","cited_by_count":4,"area":"agents"},{"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":"2406.02536","title":"Mitigate Position Bias in Large Language Models via Scaling a Single Dimension","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2502.08662","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"area":"synth"},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2412.07171","title":"Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models","created":"2024-12-10","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":"2512.21576","title":"Towards Long-window Anchoring in Vision-Language Model Distillation","created":"2025-12-25","cited_by_count":2,"area":"mllm"},{"id":"2601.00274","title":"Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems","created":"2026-01-01","cited_by_count":2,"area":"rag"},{"id":"2602.02597","title":"ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization","created":"2026-02-01","cited_by_count":2,"area":"agents"},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2409.19745","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","created":"2024-09-29","cited_by_count":1,"area":"rag"},{"id":"2502.18915","title":"END: Early Noise Dropping for Efficient and Effective Context Denoising","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2502.20405","title":"Pause-Tuning for Long-Context Comprehension: A Lightweight Approach to LLM Attention Recalibration","created":"2025-02-01","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":"2503.06949","title":"LexPro-1.0 Technical Report","created":"2025-03-10","cited_by_count":1,"area":"lr"},{"id":"2507.14849","title":"Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding","created":"2025-07-20","cited_by_count":1,"area":"lr"},{"id":"2507.22919","title":"A novel language model for predicting serious adverse event results in clinical trials from their prospective registrations","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2509.09199","title":"CCF: A Context Compression Framework for Efficient Long-Sequence Language Modeling","created":"2025-09-11","cited_by_count":1,"area":"inference"},{"id":"2509.13539","title":"Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2510.22956","title":"Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.08082","title":"Short-Context Dominance: How Much Local Context Natural Language Actually Needs?","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.13109","title":"Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2603.20578","title":"Context Cartography: Toward Structured Governance of Contextual Space in Large Language Model Systems","created":"2026-03-21","cited_by_count":1,"area":"lr"},{"id":"2604.14339","title":"Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation","created":"2026-04-15","cited_by_count":1,"area":"rag"},{"id":"2604.19777","title":"Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2606.13550","title":"Uncertainty-Aware Hybrid Retrieval for Long-Document RAG","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2606.23687","title":"Randomized YaRN Improves Length Generalization for Long-Context Reasoning","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2506.08371","title":"Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2507.07685","title":"Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought","created":"2025-07-10","cited_by_count":0,"area":"lr"},{"id":"2511.05850","title":"Retrieval Quality at Context Limit","created":"2025-11-08","cited_by_count":0,"area":null},{"id":"2605.05594","title":"The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.10045","title":"ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.28828","title":"Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2606.04596","title":"A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMs","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.27705","title":"Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.05708","title":"Akashic: A Low-Overhead LLM Inference Service with MemAttention","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.19920","title":"Learning how to Forget: Fine-tuning for Long-Context Sparse Attention","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.03148","title":"Large Language Models in Resolving Contextual Knowledge Conflicts","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10132","title":"Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.22101","title":"Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.22262","title":"Large language models in medical time series analysis","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.27380","title":"MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression","created":"2026-09-23","cited_by_count":0,"area":"rag"},{"id":"2610.00926","title":"A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform","created":"2026-10-01","cited_by_count":0,"area":"driving"}],"next_cursor":null}