{"total":190,"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":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369,"area":"rag"},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"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":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169,"area":"lr"},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162,"area":"lr"},{"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":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"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":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"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":"2204.08292","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","created":"2022-04-18","cited_by_count":68,"area":"lr"},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65,"area":null},{"id":"2402.00559","title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","created":"2024-02-01","cited_by_count":65,"area":"lr"},{"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":"2303.14725","title":"Natural Language Reasoning, A Survey","created":"2023-03-26","cited_by_count":61,"area":"lr"},{"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":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46,"area":"mllm"},{"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":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40,"area":"inference"},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37,"area":"lr"},{"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":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2210.16433","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","created":"2022-10-28","cited_by_count":24,"area":"moe"},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2301.10896","title":"Causal Reasoning of Entities and Events in Procedural Texts","created":"2023-01-26","cited_by_count":23,"area":"lr"},{"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":"2408.06793","title":"Layerwise Recurrent Router for Mixture-of-Experts","created":"2024-08-13","cited_by_count":21,"area":"moe"},{"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":"2405.06683","title":"ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization","created":"2024-05-06","cited_by_count":15,"area":"rag"},{"id":"2407.10670","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","created":"2024-07-15","cited_by_count":15,"area":"rag"},{"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":"2210.08590","title":"Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective","created":"2022-10-16","cited_by_count":14,"area":"lr"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"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":"2408.13533","title":"Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models","created":"2024-08-24","cited_by_count":13,"area":"rag"},{"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":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"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":"2201.05880","title":"Reasoning over Hybrid Chain for Table-and-Text Open Domain QA","created":"2022-01-15","cited_by_count":10,"area":"lr"},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2603.01152","title":"DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent","created":"2026-03-01","cited_by_count":10,"area":"agents"},{"id":"2204.13778","title":"Inferring Implicit Relations in Complex Questions with Language Models","created":"2022-04-28","cited_by_count":9,"area":"lr"},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"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":"2505.10089","title":"XRAG: Cross-lingual Retrieval-Augmented Generation","created":"2025-05-15","cited_by_count":9,"area":"rag"},{"id":"2203.08992","title":"AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension","created":"2022-03-16","cited_by_count":8,"area":"lr"},{"id":"2406.16086","title":"SEAM: A Stochastic Benchmark for Multi-Document Tasks","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2409.12437","title":"Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data","created":"2024-09-19","cited_by_count":8,"area":"lr"},{"id":"2506.02000","title":"NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2508.15851","title":"DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections","created":"2025-08-20","cited_by_count":8,"area":"lr"},{"id":"2508.17621","title":"Steering When Necessary: Flexible Steering Large Language Models with Backtracking","created":"2025-08-25","cited_by_count":8,"area":"mechinterp"},{"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}],"next_cursor":"100"}