{"total":75,"rows":[{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172,"area":null},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"area":null},{"id":"2110.00768","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","created":"2021-10-02","cited_by_count":96,"area":null},{"id":"2309.15427","title":"Graph Neural Prompting with Large Language Models","created":"2023-09-27","cited_by_count":64,"area":null},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2406.17761","title":"CaLMQA: Exploring culturally specific long-form question answering across 23 languages","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"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":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2109.12870","title":"MFAQ: a Multilingual FAQ Dataset","created":"2021-09-27","cited_by_count":17,"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":"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":"2304.00472","title":"Querying Large Language Models with SQL","created":"2023-04-02","cited_by_count":14,"area":null},{"id":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2205.09843","title":"Table Retrieval May Not Necessitate Table-specific Model Design","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2210.06104","title":"EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2305.05486","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","created":"2023-05-09","cited_by_count":11,"area":null},{"id":"2110.07333","title":"A Survey on Legal Question Answering Systems","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2205.00395","title":"ELQA: A Corpus of Metalinguistic Questions and Answers about English","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2112.08615","title":"Knowledge-Augmented Language Models for Cause-Effect Relation Classification","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2206.06029","title":"Mediators: Conversational Agents Explaining NLP Model Behavior","created":"2022-06-13","cited_by_count":7,"area":null},{"id":"2305.01957","title":"NorQuAD: Norwegian Question Answering Dataset","created":"2023-05-03","cited_by_count":7,"area":null},{"id":"2403.18426","title":"TriviaHG: A Dataset for Automatic Hint Generation from Factoid Questions","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2412.07420","title":"RAG-based Question Answering over Heterogeneous Data and Text","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2203.13693","title":"UKP-SQUARE: An Online Platform for Question Answering Research","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2206.13778","title":"CC-Riddle: A Question Answering Dataset of Chinese Character Riddles","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2311.14652","title":"One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space","created":"2023-11-24","cited_by_count":6,"area":null},{"id":"2112.13634","title":"A Survey on non-English Question Answering Dataset","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2204.06457","title":"The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer","created":"2022-04-13","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":"2309.08491","title":"Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","cited_by_count":5,"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":"2505.03803","title":"RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2108.12898","title":"Generating Answer Candidates for Quizzes and Answer-Aware Question Generators","created":"2021-08-29","cited_by_count":3,"area":null},{"id":"2109.12028","title":"Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2303.07069","title":"Generating multiple-choice questions for medical question answering with distractors and cue-masking","created":"2023-03-13","cited_by_count":3,"area":null},{"id":"2109.07102","title":"Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2204.08009","title":"WikiOmnia: generative QA corpus on the whole Russian Wikipedia","created":"2022-04-17","cited_by_count":2,"area":null},{"id":"2208.09316","title":"UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA","created":"2022-08-19","cited_by_count":2,"area":null},{"id":"2410.09449","title":"Continuous Risk Prediction","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2108.00719","title":"ConveRT for FAQ Answering","created":"2021-08-02","cited_by_count":1,"area":null},{"id":"2204.00556","title":"Nowruz at SemEval-2022 Task 7: Tackling Cloze Tests with Transformers and Ordinal Regression","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2207.01918","title":"Cross-Lingual QA as a Stepping Stone for Monolingual Open QA in Icelandic","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2303.03290","title":"AmQA: Amharic Question Answering Dataset","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2303.18120","title":"UKP-SQuARE v3: A Platform for Multi-Agent QA Research","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2307.11779","title":"The Extractive-Abstractive Axis: Measuring Content \"Borrowing\" in Generative Language Models","created":"2023-07-20","cited_by_count":1,"area":null},{"id":"2404.12050","title":"emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information","created":"2024-04-18","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":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2112.08578","title":"CLICKER: A Computational LInguistics Classification Scheme for Educational Resources","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2204.13943","title":"User Experience Design for Automatic Credibility Assessment of News Content About COVID-19","created":"2022-04-29","cited_by_count":0,"area":null},{"id":"2208.14602","title":"Continuous QA Learning with Structured Prompts","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2211.04946","title":"Accountable and Explainable Methods for Complex Reasoning over Text","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2303.05789","title":"AnoMalNet: Outlier Detection based Malaria Cell Image Classification Method Leveraging Deep Autoencoder","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2303.09067","title":"Secret-Keeping in Question Answering","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2303.12671","title":"Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2304.06184","title":"LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2402.11177","title":"A Question Answering Based Pipeline for Comprehensive Chinese EHR Information Extraction","created":"2024-02-17","cited_by_count":0,"area":null},{"id":"2404.03938","title":"Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2507.15581","title":"Metric assessment protocol in the context of answer fluctuation on MCQ tasks","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2510.12534","title":"ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2510.15134","title":"FarsiMCQGen: a Persian Multiple-choice Question Generation Framework","created":"2025-10-16","cited_by_count":0,"area":null}],"next_cursor":null}