{"list":"other","total":54,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2205.12685","title":"Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations","created":"2022-05-25","cited_by_count":116},{"id":"2302.13539","title":"Finding Support Examples for In-Context Learning","created":"2023-02-27","cited_by_count":104},{"id":"1409.7938","title":"Lazier Than Lazy Greedy","created":"2014-09-28","cited_by_count":99},{"id":"2006.15412","title":"Submodular Combinatorial Information Measures with Applications in Machine Learning","created":"2020-06-27","cited_by_count":88},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86},{"id":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64},{"id":"2107.05687","title":"Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers","created":"2021-07-12","cited_by_count":60},{"id":"2103.00128","title":"PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection","created":"2021-02-27","cited_by_count":51},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47},{"id":"2306.15091","title":"Understanding In-Context Learning via Supportive Pretraining Data","created":"2023-06-26","cited_by_count":41},{"id":"2310.20046","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","created":"2023-10-30","cited_by_count":37},{"id":"2112.00166","title":"TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information","created":"2021-11-30","cited_by_count":27},{"id":"2310.10873","title":"IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models","created":"2023-10-16","cited_by_count":27},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22},{"id":"2203.11027","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","created":"2022-03-14","cited_by_count":21},{"id":"1901.01153","title":"Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance","created":"2019-01-03","cited_by_count":14},{"id":"2409.12255","title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","created":"2024-09-18","cited_by_count":13},{"id":"2407.02665","title":"SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection","created":"2024-07-02","cited_by_count":8},{"id":"2310.00165","title":"SCoRe: Submodular Combinatorial Representation Learning","created":"2023-09-29","cited_by_count":7},{"id":"2101.10514","title":"How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization","created":"2021-01-26","cited_by_count":6},{"id":"2203.09073","title":"Ask to Understand: Question Generation for Multi-hop Question Answering","created":"2022-03-17","cited_by_count":2}],"next_cursor":null}