{"total":39,"rows":[{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"area":null},{"id":"2409.11136","title":"Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models","created":"2024-09-17","cited_by_count":40,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25,"area":null},{"id":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2410.03435","title":"A General Framework for Producing Interpretable Semantic Text Embeddings","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2503.22727","title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2504.18269","title":"TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2506.14407","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.12677","title":"Case-Based Decision-Theoretic Decoding with Quality Memories","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2510.17476","title":"Zoom In Disparities in Healthcare LLM Q&A","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.06458","title":"PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2603.12368","title":"Multi-Step Semantic Reasoning in Generative Retrieval","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.14473","title":"Response-Aware User Memory Selection for LLM Personalization","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.06006","title":"From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2411.13163","title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2412.20597","title":"GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2502.15692","title":"ACL-rlg: A Dataset for Reading List Generation","created":"2024-12-30","cited_by_count":0,"area":null},{"id":"2504.05125","title":"Interpretable Style Takagi-Sugeno-Kang Fuzzy Clustering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2504.20679","title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2505.11582","title":"Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.12637","title":"How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.00324","title":"Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.04731","title":"Modular Expert Merging for Biomedical Retrieval","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.20990","title":"What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2605.12028","title":"Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12313","title":"Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17379","title":"Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.17255","title":"MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.18603","title":"AutoIndex: Learning Representation Programs for Retrieval","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.27394","title":"RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.18908","title":"How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.36534","title":"Retrieval Sensitivity to Identity Signals in Queries","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}