{"total":58,"rows":[{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"area":null},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2502.18460","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","created":"2025-02-25","cited_by_count":19,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2510.11408","title":"Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification","created":"2025-10-13","cited_by_count":18,"area":null},{"id":"2504.03598","title":"EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline","created":"2025-04-04","cited_by_count":15,"area":null},{"id":"2501.18539","title":"Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method","created":"2025-01-30","cited_by_count":10,"area":"agents"},{"id":"2504.07199","title":"SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog","created":"2025-04-09","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2505.11651","title":"MIRACL-VISION: A Large, multilingual, visual document retrieval benchmark","created":"2025-05-16","cited_by_count":9,"area":"rag"},{"id":"2507.08336","title":"Distillation versus Contrastive Learning: How to Train Your Rerankers","created":"2025-07-11","cited_by_count":6,"area":"distill"},{"id":"2509.07253","title":"Benchmarking Information Retrieval Models on Complex Retrieval Tasks","created":"2025-09-08","cited_by_count":6,"area":null},{"id":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2601.01684","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","created":"2026-01-04","cited_by_count":5,"area":null},{"id":"2505.14398","title":"Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation","created":"2025-05-20","cited_by_count":4,"area":"lr"},{"id":"2604.03592","title":"Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation","created":"2026-04-04","cited_by_count":4,"area":"moe"},{"id":"2606.07923","title":"Larch: Learned Query Optimization for Semantic Predicates","created":"2026-06-06","cited_by_count":4,"area":null},{"id":"2505.09068","title":"S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"id":"2505.19356","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2512.05411","title":"A Systematic Framework for Enterprise Knowledge Retrieval: Leveraging LLM-Generated Metadata to Enhance RAG Systems","created":"2025-12-05","cited_by_count":3,"area":"rag"},{"id":"2608.21494","title":"Retrieval Needs Multivectors: An Exponential Separation","created":"2026-08-21","cited_by_count":3,"area":null},{"id":"2601.04646","title":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2503.05763","title":"GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2505.22118","title":"Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.12571","title":"DoTA-RAG: Dynamic of Thought Aggregation RAG","created":"2025-06-14","cited_by_count":1,"area":"rag"},{"id":"2512.04790","title":"Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery","created":"2025-12-04","cited_by_count":1,"area":"rag"},{"id":"2601.10321","title":"An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fit","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.13111","title":"CORE-T: COherent REtrieval of Tables for Text-to-SQL","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.06526","title":"Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2603.23972","title":"Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith","created":"2026-03-25","cited_by_count":1,"area":"rag"},{"id":"2605.12714","title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.29507","title":"Xetrieval: Mechanistically Explaining Dense Retrieval","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.19719","title":"Closing the Operational Gap in Semantic Caching","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2507.03122","title":"Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2510.05336","title":"WeatherArchive-Bench: Benchmarking Retrieval-Augmented Reasoning for Historical Weather Archives","created":"2025-10-06","cited_by_count":0,"area":"rag"},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2601.03496","title":"STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.03940","title":"Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs","created":"2026-01-07","cited_by_count":0,"area":"lr"},{"id":"2601.13932","title":"Generating consensus and dissent on massive discussion platforms with a semantic-vector model","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.21803","title":"Quantifying Retriever-Generator Alignment in RAG with Local Explanations","created":"2026-01-29","cited_by_count":0,"area":"rag"},{"id":"2604.14907","title":"Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.14188","title":"QOuLiPo: What a quantum computer sees when it reads a book","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24556","title":"The Multilingual Curse at the Retrieval Layer: Evidence from Amharic","created":"2026-05-23","cited_by_count":0,"area":"rag"},{"id":"2605.25030","title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","created":"2026-05-24","cited_by_count":0,"area":"rag"},{"id":"2606.13647","title":"SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.04581","title":"MTEB-BR: A Text Embedding Benchmark for Brazilian Portuguese","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20246","title":"What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence","created":"2026-08-20","cited_by_count":0,"area":"rag"},{"id":"2609.01379","title":"Polish ModernBERT: The Long and Short of Polish Language Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05110","title":"Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval","created":"2026-09-04","cited_by_count":0,"area":"rag"},{"id":"2609.24613","title":"UK-PRBENCH: A Paragraph-Level Precedent Retrieval Benchmark for United Kingdom Case Law","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30906","title":"ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.36376","title":"Quantization Enables Private Dense Retrieval against Malicious Service Providers","created":"2026-09-28","cited_by_count":0,"area":"rag"},{"id":"2610.04973","title":"TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}