{"list":"other","total":64,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2002.02126","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","created":"2020-02-06","cited_by_count":1139},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"1511.06939","title":"Session-based Recommendations with Recurrent Neural Networks","created":"2015-11-21","cited_by_count":695},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"1809.07426","title":"Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding","created":"2018-09-19","cited_by_count":476},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"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":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"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":"2008.07873","title":"S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization","created":"2020-08-18","cited_by_count":311},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188},{"id":"2311.00423","title":"LLMRec: Large Language Models with Graph Augmentation for Recommendation","created":"2023-11-01","cited_by_count":172},{"id":"1601.02513","title":"How to learn a graph from smooth signals","created":"2016-01-11","cited_by_count":146},{"id":"2011.01731","title":"RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms","created":"2020-11-03","cited_by_count":138},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2110.05730","title":"Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation","created":"2021-10-12","cited_by_count":121},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"1906.09217","title":"Hierarchical Gating Networks for Sequential Recommendation","created":"2019-06-21","cited_by_count":101},{"id":"2310.19488","title":"CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation","created":"2023-10-30","cited_by_count":100},{"id":"2010.13369","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","created":"2020-10-26","cited_by_count":93},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93},{"id":"2403.02545","title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","created":"2024-03-04","cited_by_count":74},{"id":"2311.01343","title":"Collaborative Large Language Model for Recommender Systems","created":"2023-11-02","cited_by_count":64},{"id":"2307.00457","title":"GenRec: Large Language Model for Generative Recommendation","created":"2023-07-02","cited_by_count":63},{"id":"2111.07337","title":"$p$-Laplacian Based Graph Neural Networks","created":"2021-11-14","cited_by_count":39},{"id":"2312.02443","title":"E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation","created":"2023-12-05","cited_by_count":39},{"id":"2208.08489","title":"Understanding Scaling Laws for Recommendation Models","created":"2022-08-17","cited_by_count":38},{"id":"2309.07602","title":"Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?","created":"2023-09-14","cited_by_count":30},{"id":"2308.07192","title":"gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling","created":"2023-08-14","cited_by_count":29},{"id":"2010.13382","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","created":"2020-10-26","cited_by_count":28},{"id":"2402.09543","title":"Rethinking Large Language Model Architectures for Sequential Recommendations","created":"2024-02-14","cited_by_count":27},{"id":"2010.04484","title":"Revisiting Alternative Experimental Settings for Evaluating Top-N Item Recommendation Algorithms","created":"2020-10-09","cited_by_count":24},{"id":"2311.11351","title":"Scaling Law of Large Sequential Recommendation Models","created":"2023-11-19","cited_by_count":23},{"id":"2311.04590","title":"Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions","created":"2023-11-08","cited_by_count":20},{"id":"2305.04619","title":"Graph Masked Autoencoder for Sequential Recommendation","created":"2023-05-08","cited_by_count":19},{"id":"2405.07580","title":"DynLLM: When Large Language Models Meet Dynamic Graph Recommendation","created":"2024-05-13","cited_by_count":12},{"id":"2302.05919","title":"Neural Node Matching for Multi-Target Cross Domain Recommendation","created":"2023-02-12","cited_by_count":8},{"id":"2310.17488","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","created":"2023-10-26","cited_by_count":8},{"id":"2311.04760","title":"Towards Open-world Cross-Domain Sequential Recommendation: A Model-Agnostic Contrastive Denoising Approach","created":"2023-11-08","cited_by_count":4}],"next_cursor":null}