{"total":44,"rows":[{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2412.14468","title":"HashAttention: Semantic Sparsity for Faster Inference","created":"2024-12-19","cited_by_count":24,"area":null},{"id":"2411.03538","title":"Long Context RAG Performance of Large Language Models","created":"2024-11-05","cited_by_count":23,"area":null},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2505.11545","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","created":"2025-05-14","cited_by_count":17,"area":null},{"id":"2410.10450","title":"KBLaM: Knowledge Base augmented Language Model","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2502.02789","title":"Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2506.06091","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2602.15313","title":"Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory","created":"2026-02-17","cited_by_count":8,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"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":"2507.04723","title":"LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework","created":"2025-07-07","cited_by_count":5,"area":null},{"id":"2411.18831","title":"Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark","created":"2024-11-28","cited_by_count":4,"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":"2505.02763","title":"Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2505.11754","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.17484","title":"Learning When to Attend: Conditional Memory Access for Long-Context LLMs","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2603.20105","title":"The $\\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $\\lambda$-Calculus","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2501.16220","title":"DBRouting: Routing End User Queries to Databases for Answerability","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2504.16204","title":"Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Design","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2601.13007","title":"ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.13418","title":"Text Has Curvature","created":"2026-02-13","cited_by_count":2,"area":null},{"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":"2410.13037","title":"LFOSum: Summarizing Long-form Opinions with Large Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2507.08704","title":"Knowledge Fusion via Bidirectional Information Aggregation","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2602.18448","title":"INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2606.20898","title":"The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2411.07870","title":"Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2506.12149","title":"Maximally-Informative Retrieval for State Space Model Generation","created":"2025-06-13","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":"2512.08088","title":"Adaptation of Embedding Models to Financial Filings via LLM Distillation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.15658","title":"Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.24376","title":"GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.11759","title":"Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure","created":"2026-04-13","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":"2607.20470","title":"PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.23265","title":"EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00759","title":"Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.22880","title":"Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.24885","title":"The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.25028","title":"Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum","created":"2026-08-18","cited_by_count":0,"area":null}],"next_cursor":null}