{"list":"other","total":53,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1703.04247","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","created":"2017-03-13","cited_by_count":676},{"id":"2203.13366","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","created":"2022-03-24","cited_by_count":402},{"id":"1708.05123","title":"Deep & Cross Network for Ad Click Predictions","created":"2017-08-17","cited_by_count":393},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2305.00447","title":"TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation","created":"2023-04-30","cited_by_count":337},{"id":"2008.13535","title":"DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems","created":"2020-08-19","cited_by_count":327},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294},{"id":"1803.05170","title":"xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems","created":"2018-03-14","cited_by_count":278},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2304.10149","title":"Is ChatGPT a Good Recommender? A Preliminary Study","created":"2023-04-20","cited_by_count":193},{"id":"1708.05027","title":"Neural Factorization Machines for Sparse Predictive Analytics","created":"2017-08-16","cited_by_count":183},{"id":"2305.07001","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","created":"2023-05-11","cited_by_count":168},{"id":"2205.08084","title":"M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems","created":"2022-05-17","cited_by_count":152},{"id":"2305.13731","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","created":"2023-05-23","cited_by_count":149},{"id":"1611.00144","title":"Product-based Neural Networks for User Response Prediction","created":"2016-11-01","cited_by_count":145},{"id":"2306.05817","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","created":"2023-06-09","cited_by_count":142},{"id":"1708.04617","title":"Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks","created":"2017-08-15","cited_by_count":126},{"id":"2206.05941","title":"Towards Universal Sequence Representation Learning for Recommender Systems","created":"2022-06-13","cited_by_count":121},{"id":"2305.06474","title":"Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction","created":"2023-05-10","cited_by_count":116},{"id":"2305.06569","title":"How to Index Item IDs for Recommendation Foundation Models","created":"2023-05-11","cited_by_count":102},{"id":"1905.09433","title":"FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction","created":"2019-05-23","cited_by_count":83},{"id":"2308.11131","title":"ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation","created":"2023-08-22","cited_by_count":77},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76},{"id":"2306.10933","title":"Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models","created":"2023-06-19","cited_by_count":74},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"1910.05552","title":"Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction","created":"2019-10-12","cited_by_count":54},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45},{"id":"1807.00311","title":"Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data","created":"2018-07-01","cited_by_count":44},{"id":"2305.12090","title":"UP5: Unbiased Foundation Model for Fairness-aware Recommendation","created":"2023-05-20","cited_by_count":38},{"id":"2104.10584","title":"Deep Learning for Click-Through Rate Estimation","created":"2021-04-21","cited_by_count":33},{"id":"2209.08060","title":"PTab: Using the Pre-trained Language Model for Modeling Tabular Data","created":"2022-09-15","cited_by_count":30},{"id":"1904.04447","title":"Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction","created":"2019-04-09","cited_by_count":26},{"id":"2305.15756","title":"UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation","created":"2023-05-25","cited_by_count":20},{"id":"2104.06077","title":"An Adversarial Imitation Click Model for Information Retrieval","created":"2021-04-13","cited_by_count":18},{"id":"2204.08758","title":"Enhancing CTR Prediction with Context-Aware Feature Representation Learning","created":"2022-04-19","cited_by_count":17},{"id":"2206.08621","title":"A Graph-Enhanced Click Model for Web Search","created":"2022-06-17","cited_by_count":17},{"id":"2105.11866","title":"GraphFM: Graph Factorization Machines for Feature Interaction Modeling","created":"2021-05-25","cited_by_count":13},{"id":"2211.09303","title":"A Bird's-eye View of Reranking: from List Level to Page Level","created":"2022-11-17","cited_by_count":13},{"id":"2206.08604","title":"An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages","created":"2022-06-17","cited_by_count":10},{"id":"2308.01737","title":"MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction","created":"2023-08-03","cited_by_count":10},{"id":"2105.08649","title":"DCAP: Deep Cross Attentional Product Network for User Response Prediction","created":"2021-05-18","cited_by_count":5}],"next_cursor":null}