{"total":18,"rows":[{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2507.20804","title":"MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs","created":"2025-07-28","cited_by_count":16,"area":null},{"id":"2410.03198","title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2509.19345","title":"SCORE: A Semantic Evaluation Framework for Generative Document Parsing","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2606.05749","title":"MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2501.11782","title":"Human-AI Collaborative Game Testing with Vision Language Models","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2607.19865","title":"DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2506.07754","title":"Comparing Credit Risk Estimates in the Gen-AI Era","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2512.04445","title":"Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.18401","title":"Superlinear Multi-Step Attention","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.00585","title":"Exploring Information Seeking Agent Consolidation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2608.00036","title":"XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.08459","title":"Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.29990","title":"Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.33642","title":"Learning to Learn from Context: Synthetic Training from Perturbed Public Documents","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}