{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2010.03622","title":"Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data","created":"2020-10-07","cited_by_count":180},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85},{"id":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50},{"id":"2102.11203","title":"A Theory of Label Propagation for Subpopulation Shift","created":"2021-02-22","cited_by_count":48},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34},{"id":"2105.11653","title":"Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets","created":"2021-05-25","cited_by_count":11},{"id":"2212.06921","title":"Losses over Labels: Weakly Supervised Learning via Direct Loss Construction","created":"2022-12-13","cited_by_count":11},{"id":"2210.03594","title":"Label Propagation with Weak Supervision","created":"2022-10-07","cited_by_count":9},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9},{"id":"2409.09721","title":"Finetuning CLIP to Reason about Pairwise Differences","created":"2024-09-15","cited_by_count":6}],"next_cursor":null}