{"total":98,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2305.13062","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2210.06628","title":"OpenCQA: Open-ended Question Answering with Charts","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2109.04312","title":"MATE: Multi-view Attention for Table Transformer Efficiency","created":"2021-09-09","cited_by_count":54,"area":null},{"id":"2306.15681","title":"ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram","created":"2023-06-21","cited_by_count":54,"area":null},{"id":"2310.18652","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","created":"2023-10-28","cited_by_count":53,"area":null},{"id":"2208.13629","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","created":"2022-08-29","cited_by_count":52,"area":null},{"id":"2210.08817","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2205.12665","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","created":"2022-05-25","cited_by_count":42,"area":null},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39,"area":null},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2212.08632","title":"Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","created":"2022-12-16","cited_by_count":28,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2411.04075","title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","created":"2024-11-06","cited_by_count":27,"area":null},{"id":"2204.11677","title":"Conversational Question Answering on Heterogeneous Sources","created":"2022-04-25","cited_by_count":26,"area":null},{"id":"2310.07875","title":"TabLib: A Dataset of 627M Tables with Context","created":"2023-10-11","cited_by_count":23,"area":null},{"id":"2306.16762","title":"Unified Language Representation for Question Answering over Text, Tables, and Images","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2309.04790","title":"MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images","created":"2023-09-09","cited_by_count":18,"area":null},{"id":"2205.01290","title":"DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries","created":"2022-05-03","cited_by_count":17,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2505.14661","title":"Abacus: A Cost-Based Optimizer for Semantic Operator Systems","created":"2025-05-20","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2411.09547","title":"Piecing It All Together: Verifying Multi-Hop Multimodal Claims","created":"2024-11-14","cited_by_count":12,"area":null},{"id":"2108.04049","title":"Multi-modal Retrieval of Tables and Texts Using Tri-encoder Models","created":"2021-08-09","cited_by_count":11,"area":null},{"id":"2304.09660","title":"MPMQA: Multimodal Question Answering on Product Manuals","created":"2023-04-19","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2306.16713","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2310.13265","title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model","created":"2023-10-20","cited_by_count":10,"area":null},{"id":"2409.08250","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2509.18436","title":"Memory-QA: Answering Recall Questions Based on Multimodal Memories","created":"2025-09-22","cited_by_count":10,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2408.13860","title":"Knowledge-Aware Reasoning over Multimodal Semi-structured Tables","created":"2024-08-25","cited_by_count":9,"area":null},{"id":"2505.21771","title":"MMTABREAL: Real-World Benchmark for Multimodal Table Understanding","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2511.01716","title":"SemBench: A Benchmark for Semantic Query Processing Engines","created":"2025-11-03","cited_by_count":9,"area":null},{"id":"2511.22154","title":"WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios","created":"2025-11-27","cited_by_count":9,"area":null},{"id":"2402.07742","title":"Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search","created":"2024-02-12","cited_by_count":8,"area":null},{"id":"2402.10812","title":"Exploring Hybrid Question Answering via Program-based Prompting","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2104.08647","title":"Question Decomposition with Dependency Graphs","created":"2021-04-17","cited_by_count":7,"area":null},{"id":"2212.13465","title":"A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions","created":"2022-12-27","cited_by_count":7,"area":null},{"id":"2303.02635","title":"VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning","created":"2023-03-05","cited_by_count":7,"area":null},{"id":"2310.15075","title":"TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answering","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2203.03819","title":"Table Structure Recognition with Conditional Attention","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2210.05991","title":"Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2302.02978","title":"MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2307.04643","title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2309.08922","title":"Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models","created":"2023-09-16","cited_by_count":6,"area":null},{"id":"2309.11049","title":"Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2206.12449","title":"OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience","created":"2022-06-24","cited_by_count":5,"area":null},{"id":"2310.09696","title":"Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering","created":"2023-10-15","cited_by_count":5,"area":null},{"id":"2401.11631","title":"Text-to-Image Cross-Modal Generation: A Systematic Review","created":"2024-01-21","cited_by_count":5,"area":null},{"id":"2510.09671","title":"Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2109.06480","title":"Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification","created":"2021-09-14","cited_by_count":4,"area":null},{"id":"2410.21414","title":"CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2111.05890","title":"Multimodal End-to-End Group Emotion Recognition using Cross-Modal Attention","created":"2021-11-10","cited_by_count":3,"area":null},{"id":"2504.08269","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering","created":"2025-04-11","cited_by_count":3,"area":null},{"id":"2605.08146","title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2608.03451","title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2307.04532","title":"Read, Look or Listen? What's Needed for Solving a Multimodal Dataset","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2308.11257","title":"HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2406.13232","title":"Towards Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2411.11344","title":"Mitigating Knowledge Conflicts in Language Model-Driven Question Answering","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2508.16051","title":"MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2509.04770","title":"Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework","created":"2025-09-05","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":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.10460","title":"LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2501.04173","title":"Multimodal Multihop Source Retrieval for Web Question Answering","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2506.09738","title":"Towards Multimodal Graph Large Language Model","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2512.11067","title":"KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.00996","title":"DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.01701","title":"Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2606.01285","title":"Knowledge-Intensive Video Generation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.28329","title":"$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.12310","title":"LakeQuest: A Three-Domain Benchmark for Grounded Question Answering across Data Lakes","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.16208","title":"ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.25765","title":"WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.30468","title":"Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.08896","title":"Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.28761","title":"KathDB-FAO: Synthesized Query Plans in a Multimodal DBMS","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.17057","title":"VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}