{"total":331,"rows":[{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543,"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":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356,"area":null},{"id":"2312.14197","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","created":"2023-12-21","cited_by_count":264,"area":"safety"},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244,"area":null},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243,"area":null},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211,"area":null},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202,"area":"rag"},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195,"area":"rag"},{"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":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2210.02627","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","created":"2022-10-06","cited_by_count":127,"area":"rag"},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"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":"2401.10225","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","created":"2024-01-18","cited_by_count":90,"area":"rag"},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85,"area":null},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2311.08377","title":"Learning to Filter Context for Retrieval-Augmented Generation","created":"2023-11-14","cited_by_count":83,"area":"rag"},{"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":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"area":null},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"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":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62,"area":null},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58,"area":"lr"},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57,"area":null},{"id":"2105.04623","title":"Improving Factual Consistency of Abstractive Summarization via Question Answering","created":"2021-05-10","cited_by_count":55,"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":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53,"area":"rag"},{"id":"2109.04655","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","created":"2021-09-10","cited_by_count":52,"area":null},{"id":"2301.03282","title":"Universal Information Extraction as Unified Semantic Matching","created":"2023-01-09","cited_by_count":48,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2203.00343","title":"Read before Generate! Faithful Long Form Question Answering with Machine Reading","created":"2022-03-01","cited_by_count":47,"area":null},{"id":"2107.03444","title":"Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text","created":"2021-07-07","cited_by_count":45,"area":null},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2406.18664","title":"Evaluating Copyright Takedown Methods for Language Models","created":"2024-06-26","cited_by_count":43,"area":null},{"id":"2305.11541","title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","created":"2023-05-19","cited_by_count":41,"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":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2510.05445","title":"AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering","created":"2025-10-06","cited_by_count":32,"area":"agents"},{"id":"2106.00874","title":"Conversational Question Answering: A Survey","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2401.15422","title":"A Survey on Data Augmentation in Large Model Era","created":"2024-01-27","cited_by_count":31,"area":"diffusion"},{"id":"2109.03438","title":"ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections","created":"2021-09-08","cited_by_count":30,"area":null},{"id":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28,"area":null},{"id":"2110.08175","title":"MixQG: Neural Question Generation with Mixed Answer Types","created":"2021-10-15","cited_by_count":28,"area":null},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"area":null},{"id":"2404.16032","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","created":"2024-04-24","cited_by_count":27,"area":"rag"},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2211.08264","title":"QAmeleon: Multilingual QA with Only 5 Examples","created":"2022-11-15","cited_by_count":25,"area":null},{"id":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2602.06358","title":"SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass","created":"2026-02-06","cited_by_count":25,"area":null},{"id":"2408.04259","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","created":"2024-08-08","cited_by_count":24,"area":"rag"},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2103.11263","title":"Self-Supervised Test-Time Learning for Reading Comprehension","created":"2021-03-20","cited_by_count":22,"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":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2205.02014","title":"On Continual Model Refinement in Out-of-Distribution Data Streams","created":"2022-05-04","cited_by_count":22,"area":null},{"id":"2403.08192","title":"MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension","created":"2024-03-13","cited_by_count":22,"area":null},{"id":"2109.07954","title":"Improving Unsupervised Question Answering via Summarization-Informed Question Generation","created":"2021-09-16","cited_by_count":21,"area":null},{"id":"2204.10555","title":"KALA: Knowledge-Augmented Language Model Adaptation","created":"2022-04-22","cited_by_count":21,"area":null},{"id":"2205.04040","title":"ProQA: Structural Prompt-based Pre-training for Unified Question Answering","created":"2022-05-09","cited_by_count":21,"area":null},{"id":"2404.06809","title":"Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation","created":"2024-04-10","cited_by_count":21,"area":"rag"},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2403.17848","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","created":"2024-03-26","cited_by_count":20,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"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":"2302.01691","title":"LIQUID: A Framework for List Question Answering Dataset Generation","created":"2023-02-03","cited_by_count":19,"area":null},{"id":"2409.09916","title":"SFR-RAG: Towards Contextually Faithful LLMs","created":"2024-09-16","cited_by_count":19,"area":"rag"},{"id":"2105.02274","title":"Rethinking Search: Making Domain Experts out of Dilettantes","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2112.08560","title":"Block-Skim: Efficient Question Answering for Transformer","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2502.08767","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","created":"2025-02-12","cited_by_count":18,"area":null},{"id":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2505.21700","title":"Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis","created":"2025-05-27","cited_by_count":17,"area":"rag"},{"id":"2510.07475","title":"MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference","created":"2025-10-08","cited_by_count":17,"area":"agents"},{"id":"2104.12377","title":"DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension","created":"2021-04-26","cited_by_count":16,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2105.12969","title":"Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2109.04780","title":"RoR: Read-over-Read for Long Document Machine Reading Comprehension","created":"2021-09-10","cited_by_count":15,"area":null},{"id":"2109.13880","title":"Single-dataset Experts for Multi-dataset Question Answering","created":"2021-09-28","cited_by_count":15,"area":null},{"id":"2112.01922","title":"MetaQA: Combining Expert Agents for Multi-Skill Question Answering","created":"2021-12-03","cited_by_count":15,"area":null}],"next_cursor":"100"}