{"total":161,"rows":[{"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":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"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":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"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":"2108.06314","title":"A Dataset for Answering Time-Sensitive Questions","created":"2021-08-13","cited_by_count":154,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100,"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":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","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":"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":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62,"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":"2109.04655","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","created":"2021-09-10","cited_by_count":52,"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":"2410.03953","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","created":"2024-10-04","cited_by_count":42,"area":null},{"id":"2411.06176","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","created":"2024-11-09","cited_by_count":36,"area":null},{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"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":"2110.08455","title":"Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey","created":"2021-10-16","cited_by_count":33,"area":null},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"area":null},{"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":"2110.08175","title":"MixQG: Neural Question Generation with Mixed Answer Types","created":"2021-10-15","cited_by_count":28,"area":null},{"id":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","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":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2109.03423","title":"It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books","created":"2021-09-08","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":"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":"2204.12755","title":"A Thorough Examination on Zero-shot Dense Retrieval","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2108.13854","title":"Contrastive Domain Adaptation for Question Answering using Limited Text Corpora","created":"2021-08-31","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":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"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":"2110.08555","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","created":"2021-10-16","cited_by_count":17,"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":"2210.05197","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","created":"2022-10-11","cited_by_count":17,"area":null},{"id":"2406.14394","title":"SEC-QA: A Systematic Evaluation Corpus for Financial QA","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2106.03826","title":"Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study","created":"2021-06-07","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},{"id":"2202.06219","title":"PQuAD: A Persian Question Answering Dataset","created":"2022-02-13","cited_by_count":14,"area":null},{"id":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"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":"2212.10002","title":"Defending Against Disinformation Attacks in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2310.05007","title":"MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2202.00254","title":"Active Learning Over Multiple Domains in Natural Language Tasks","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2609.00829","title":"HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution","created":"2026-09-01","cited_by_count":9,"area":null},{"id":"2109.12264","title":"More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering","created":"2021-09-25","cited_by_count":8,"area":null},{"id":"2110.01552","title":"Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2302.04618","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","created":"2023-02-09","cited_by_count":8,"area":null},{"id":"2311.13565","title":"Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering","created":"2023-11-22","cited_by_count":8,"area":null},{"id":"2403.01382","title":"Automatic Question-Answer Generation for Long-Tail Knowledge","created":"2024-03-03","cited_by_count":8,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2106.04134","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2112.08357","title":"Design Challenges for a Multi-Perspective Search Engine","created":"2021-12-15","cited_by_count":7,"area":null},{"id":"2205.11024","title":"Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2209.04998","title":"Domain Adaptation for Question Answering via Question Classification","created":"2022-09-12","cited_by_count":7,"area":null},{"id":"2212.09912","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2310.10920","title":"NuclearQA: A Human-Made Benchmark for Language Models for the Nuclear Domain","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2110.04741","title":"Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2205.03071","title":"KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering","created":"2022-05-06","cited_by_count":6,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2306.06779","title":"Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering","created":"2023-06-11","cited_by_count":6,"area":null},{"id":"2405.10725","title":"INDUS: Effective and Efficient Language Models for Scientific Applications","created":"2024-05-17","cited_by_count":6,"area":null},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6,"area":null},{"id":"2503.18063","title":"Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning","created":"2025-03-23","cited_by_count":6,"area":null},{"id":"2106.03530","title":"CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2110.04889","title":"Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation","created":"2021-10-10","cited_by_count":5,"area":null},{"id":"2205.07257","title":"Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2212.10381","title":"To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2306.04101","title":"Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2306.05083","title":"Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2312.04362","title":"PCoQA: Persian Conversational Question Answering Dataset","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","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":"2103.02537","title":"Weakly-Supervised Open-Retrieval Conversational Question Answering","created":"2021-03-03","cited_by_count":4,"area":null}],"next_cursor":"100"}