{"total":19,"rows":[{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12,"area":null},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2502.14901","title":"Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2409.18164","title":"Data-Prep-Kit: getting your data ready for LLM application development","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2509.11937","title":"MMORE: Massive Multimodal Open RAG & Extraction","created":"2025-09-15","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":"2502.15718","title":"Making Sense of Data in the Wild: Data Analysis Automation at Scale","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2507.20520","title":"AQUA: A Large Language Model for Aquaculture & Fisheries","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2510.19723","title":"From Answers to Guidance: A Proactive Dialogue System for Legal Documents","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2605.18818","title":"Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2608.09093","title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2504.19695","title":"SubGrapher: Visual Fingerprinting of Chemical Structures","created":"2025-04-28","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":"2601.21766","title":"CoFrGeNet: Continued Fraction Architectures for Language Generation","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.02276","title":"De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.07401","title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2609.20574","title":"DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.07091","title":"Smart Content Ingestion for Generative AI Workloads","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}