{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"1706.03872","title":"Six Challenges for Neural Machine Translation","created":"2017-06-12","cited_by_count":335},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"2010.05731","title":"Probing Pretrained Language Models for Lexical Semantics","created":"2020-10-12","cited_by_count":156},{"id":"2005.10283","title":"Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation","created":"2020-05-20","cited_by_count":138},{"id":"2006.01912","title":"On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior","created":"2020-06-02","cited_by_count":119},{"id":"2010.02650","title":"If beam search is the answer, what was the question?","created":"2020-10-06","cited_by_count":116},{"id":"2212.12131","title":"Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?","created":"2022-12-23","cited_by_count":113},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"2304.04736","title":"On the Possibilities of AI-Generated Text Detection","created":"2023-04-10","cited_by_count":88},{"id":"1912.00903","title":"ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation","created":"2019-12-02","cited_by_count":66},{"id":"2109.07020","title":"Frequency Effects on Syntactic Rule Learning in Transformers","created":"2021-09-14","cited_by_count":59},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58},{"id":"2005.09471","title":"Human Sentence Processing: Recurrence or Attention?","created":"2020-05-19","cited_by_count":51},{"id":"2010.07891","title":"Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention","created":"2020-10-15","cited_by_count":45},{"id":"2304.11389","title":"Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens","created":"2023-04-22","cited_by_count":41},{"id":"1805.04218","title":"Deep RNNs Encode Soft Hierarchical Syntax","created":"2018-05-11","cited_by_count":34},{"id":"2010.06396","title":"Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension","created":"2020-10-13","cited_by_count":29},{"id":"2104.05433","title":"Multilingual Language Models Predict Human Reading Behavior","created":"2021-04-12","cited_by_count":29},{"id":"1902.10068","title":"Entity Recognition at First Sight: Improving NER with Eye Movement Information","created":"2019-02-26","cited_by_count":26},{"id":"1906.11889","title":"Deep Eyedentification: Biometric Identification using Micro-Movements of the Eye","created":"2019-06-20","cited_by_count":25},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22},{"id":"2009.06171","title":"GazeBase: A Large-Scale, Multi-Stimulus, Longitudinal Eye Movement Dataset","created":"2020-09-14","cited_by_count":20},{"id":"2009.14780","title":"Bridging Information-Seeking Human Gaze and Machine Reading Comprehension","created":"2020-09-30","cited_by_count":20},{"id":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20},{"id":"1701.05581","title":"Leveraging Cognitive Features for Sentiment Analysis","created":"2017-01-19","cited_by_count":19},{"id":"2211.14301","title":"On the Effect of Anticipation on Reading Times","created":"2022-11-25","cited_by_count":19},{"id":"2304.10784","title":"Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading","created":"2023-04-21","cited_by_count":19},{"id":"2403.01152","title":"A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization","created":"2024-03-02","cited_by_count":19},{"id":"2011.04592","title":"Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze","created":"2020-11-09","cited_by_count":16},{"id":"2302.05721","title":"Synthesizing Human Gaze Feedback for Improved NLP Performance","created":"2023-02-11","cited_by_count":16},{"id":"2310.15587","title":"ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts","created":"2023-10-24","cited_by_count":14},{"id":"1804.07329","title":"Assessing Language Proficiency from Eye Movements in Reading","created":"2018-04-19","cited_by_count":12},{"id":"1608.05604","title":"Modeling Human Reading with Neural Attention","created":"2016-08-19","cited_by_count":10},{"id":"2210.09819","title":"Eye-tracking based classification of Mandarin Chinese readers with and without dyslexia using neural sequence models","created":"2022-10-18","cited_by_count":10},{"id":"1810.04839","title":"Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour","created":"2018-10-11","cited_by_count":9},{"id":"2005.12078","title":"Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour","created":"2020-05-25","cited_by_count":9},{"id":"2402.13956","title":"Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment","created":"2024-02-21","cited_by_count":9},{"id":"2310.14676","title":"Pre-Trained Language Models Augmented with Synthetic Scanpaths for Natural Language Understanding","created":"2023-10-23","cited_by_count":8},{"id":"2204.13311","title":"The Copenhagen Corpus of Eye Tracking Recordings from Natural Reading of Danish Texts","created":"2022-04-28","cited_by_count":7},{"id":"2303.17876","title":"WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset","created":"2023-03-31","cited_by_count":6},{"id":"2403.00506","title":"PoTeC: A German Naturalistic Eye-tracking-while-reading Corpus","created":"2024-03-01","cited_by_count":5},{"id":"2404.00620","title":"Reporting Eye-Tracking Data Quality: Towards a New Standard","created":"2024-03-31","cited_by_count":4},{"id":"2312.01114","title":"TURead: An eye movement dataset of Turkish reading","created":"2023-12-02","cited_by_count":3},{"id":"2311.06095","title":"Dual input stream transformer for vertical drift correction in eye-tracking reading data","created":"2023-11-10","cited_by_count":2},{"id":"2406.04988","title":"Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences","created":"2024-06-07","cited_by_count":2}],"next_cursor":null}