{"total":128,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486,"area":null},{"id":"2105.07624","title":"TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance","created":"2021-05-17","cited_by_count":408,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2310.06271","title":"Towards Mitigating Hallucination in Large Language Models via Self-Reflection","created":"2023-10-10","cited_by_count":81,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65,"area":null},{"id":"2101.00436","title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","created":"2021-01-02","cited_by_count":63,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2404.13207","title":"STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases","created":"2024-04-19","cited_by_count":55,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2305.01526","title":"Huatuo-26M, a Large-scale Chinese Medical QA Dataset","created":"2023-05-02","cited_by_count":46,"area":null},{"id":"2108.00648","title":"From LSAT: The Progress and Challenges of Complex Reasoning","created":"2021-08-02","cited_by_count":43,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"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":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2110.13472","title":"Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable","created":"2021-10-26","cited_by_count":35,"area":null},{"id":"2509.02785","title":"DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off","created":"2025-09-02","cited_by_count":34,"area":null},{"id":"2110.06884","title":"ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers","created":"2021-10-13","cited_by_count":29,"area":null},{"id":"2103.14349","title":"DAGN: Discourse-Aware Graph Network for Logical Reasoning","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"area":null},{"id":"2305.15387","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","created":"2023-05-24","cited_by_count":28,"area":null},{"id":"2311.04284","title":"CRAB: Assessing the Strength of Causal Relationships Between Real-world Events","created":"2023-11-07","cited_by_count":28,"area":null},{"id":"2205.08184","title":"SKILL: Structured Knowledge Infusion for Large Language Models","created":"2022-05-17","cited_by_count":27,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2109.04912","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","created":"2021-09-10","cited_by_count":22,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2203.11027","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2205.09226","title":"Modeling Multi-hop Question Answering as Single Sequence Prediction","created":"2022-05-18","cited_by_count":21,"area":null},{"id":"2106.01074","title":"Database Reasoning Over Text","created":"2021-06-02","cited_by_count":20,"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":"2210.14353","title":"RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering","created":"2022-10-25","cited_by_count":19,"area":null},{"id":"2408.15903","title":"LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments","created":"2024-08-28","cited_by_count":18,"area":null},{"id":"2107.11879","title":"Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2111.09714","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","created":"2021-11-18","cited_by_count":17,"area":null},{"id":"2109.12655","title":"QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions","created":"2021-09-26","cited_by_count":16,"area":null},{"id":"2408.03247","title":"Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons","created":"2024-08-06","cited_by_count":16,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2305.12086","title":"Prefix Propagation: Parameter-Efficient Tuning for Long Sequences","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2103.12876","title":"Complex Factoid Question Answering with a Free-Text Knowledge Graph","created":"2021-03-23","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2107.11823","title":"Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy","created":"2021-07-25","cited_by_count":13,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"area":null},{"id":"2103.16929","title":"Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2104.08413","title":"Sequential Cross-Document Coreference Resolution","created":"2021-04-17","cited_by_count":12,"area":null},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2210.11794","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","created":"2022-10-21","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":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11,"area":null},{"id":"2207.10284","title":"Multi Resolution Analysis (MRA) for Approximate Self-Attention","created":"2022-07-21","cited_by_count":11,"area":null},{"id":"2106.00200","title":"Iterative Hierarchical Attention for Answering Complex Questions over Long Documents","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2403.05266","title":"ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models","created":"2024-03-08","cited_by_count":9,"area":null},{"id":"2406.16086","title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","created":"2024-06-23","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":"2210.11705","title":"Efficiently Tuned Parameters are Task Embeddings","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2307.03115","title":"KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2203.12276","title":"ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention","created":"2022-03-23","cited_by_count":6,"area":null},{"id":"2305.04241","title":"Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2310.15372","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2509.07253","title":"Benchmarking Information Retrieval Models on Complex Retrieval Tasks","created":"2025-09-08","cited_by_count":6,"area":null},{"id":"2605.19577","title":"GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment","created":"2026-05-19","cited_by_count":6,"area":null},{"id":"2101.05988","title":"Coarse-grained decomposition and fine-grained interaction for multi-hop question answering","created":"2021-01-15","cited_by_count":5,"area":null},{"id":"2502.12328","title":"LM Agents for Coordinating Multi-User Information Gathering","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2509.18168","title":"HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2101.06400","title":"ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks","created":"2021-01-16","cited_by_count":4,"area":null},{"id":"2102.03741","title":"Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering","created":"2021-02-07","cited_by_count":4,"area":null},{"id":"2112.09658","title":"Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering","created":"2021-12-17","cited_by_count":4,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2210.11870","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2212.09512","title":"Rethinking Label Smoothing on Multi-hop Question Answering","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2308.06431","title":"Performance Prediction for Multi-hop Questions","created":"2023-08-12","cited_by_count":4,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2209.06923","title":"Prompt-based Conservation Learning for Multi-hop Question Answering","created":"2022-09-14","cited_by_count":3,"area":null},{"id":"2303.06675","title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","created":"2023-03-12","cited_by_count":3,"area":null},{"id":"2101.07632","title":"Situation and Behavior Understanding by Trope Detection on Films","created":"2021-01-19","cited_by_count":2,"area":null},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2103.11643","title":"Complementary Evidence Identification in Open-Domain Question Answering","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2104.08744","title":"Generative Context Pair Selection for Multi-hop Question Answering","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2203.09073","title":"Ask to Understand: Question Generation for Multi-hop Question Answering","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2212.10019","title":"When Do Decompositions Help for Machine Reading?","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2402.14522","title":"Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2501.11128","title":"A Collection of Question Answering Datasets for Norwegian","created":"2025-01-19","cited_by_count":2,"area":null},{"id":"2604.24814","title":"SWE-QA: A Dataset and Benchmark for Complex Code Understanding","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2105.03775","title":"NLP-IIS@UT at SemEval-2021 Task 4: Machine Reading Comprehension using the Long Document Transformer","created":"2021-05-08","cited_by_count":1,"area":null},{"id":"2107.00841","title":"ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension","created":"2021-07-02","cited_by_count":1,"area":null},{"id":"2202.06690","title":"ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2212.04070","title":"A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics","created":"2022-12-08","cited_by_count":1,"area":null}],"next_cursor":"100"}