{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"1806.02920","title":"GAIN: Missing Data Imputation using Generative Adversarial Nets","created":"2018-06-07","cited_by_count":352},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"1807.03653","title":"Handling Incomplete Heterogeneous Data using VAEs","created":"2018-07-10","cited_by_count":149},{"id":"2004.00584","title":"Deep Entity Matching with Pre-Trained Language Models","created":"2020-04-01","cited_by_count":144},{"id":"2311.09206","title":"TableLlama: Towards Open Large Generalist Models for Tables","created":"2023-11-15","cited_by_count":137},{"id":"2105.02584","title":"TABBIE: Pretrained Representations of Tabular Data","created":"2021-05-06","cited_by_count":111},{"id":"2304.09433","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","created":"2023-04-19","cited_by_count":111},{"id":"2301.08721","title":"Batch Prompting: Efficient Inference with Large Language Model APIs","created":"2023-01-19","cited_by_count":85},{"id":"1702.00820","title":"HoloClean: Holistic Data Repairs with Probabilistic Inference","created":"2017-02-02","cited_by_count":79},{"id":"2305.15038","title":"Is GPT-4 a Good Data Analyst?","created":"2023-05-24","cited_by_count":70},{"id":"2310.09263","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","created":"2023-10-13","cited_by_count":69},{"id":"2310.16836","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","created":"2023-10-25","cited_by_count":69},{"id":"1806.01264","title":"OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]","created":"2018-06-01","cited_by_count":63},{"id":"2009.07162","title":"Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product","created":"2020-09-15","cited_by_count":39},{"id":"2210.01922","title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning","created":"2022-10-04","cited_by_count":38},{"id":"2104.01785","title":"Annotating Columns with Pre-trained Language Models","created":"2021-04-05","cited_by_count":37},{"id":"1901.00735","title":"Dataset search: a survey","created":"2019-01-03","cited_by_count":36},{"id":"2010.07386","title":"Valentine: Evaluating Matching Techniques for Dataset Discovery","created":"2020-10-14","cited_by_count":35},{"id":"2308.16361","title":"Large Language Models as Data Preprocessors","created":"2023-08-30","cited_by_count":34},{"id":"2209.13589","title":"SANTOS: Relationship-based Semantic Table Union Search","created":"2022-09-27","cited_by_count":32},{"id":"1904.02285","title":"HoloDetect: Few-Shot Learning for Error Detection","created":"2019-04-04","cited_by_count":31},{"id":"2011.10427","title":"Dataset Discovery in Data Lakes","created":"2020-11-20","cited_by_count":31},{"id":"2310.11244","title":"Entity Matching using Large Language Models","created":"2023-10-17","cited_by_count":31},{"id":"2310.12537","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","created":"2023-10-19","cited_by_count":20},{"id":"2306.00745","title":"Column Type Annotation using ChatGPT","created":"2023-06-01","cited_by_count":19},{"id":"2106.09592","title":"Data Lakes: A Survey of Functions and Systems","created":"2021-06-17","cited_by_count":15},{"id":"2212.07588","title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models","created":"2022-12-15","cited_by_count":15},{"id":"2311.06330","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","created":"2023-11-10","cited_by_count":11},{"id":"1503.00303","title":"Truth Finding on the Deep Web: Is the Problem Solved?","created":"2015-03-01","cited_by_count":10},{"id":"2007.11838","title":"PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming","created":"2020-07-23","cited_by_count":10},{"id":"2106.16057","title":"DAEMA: Denoising Autoencoder with Mask Attention","created":"2021-06-30","cited_by_count":8},{"id":"2311.06517","title":"BClean: A Bayesian Data Cleaning System","created":"2023-11-11","cited_by_count":2}],"next_cursor":null}