{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"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":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84},{"id":"2312.02406","title":"Efficient Online Data Mixing For Language Model Pre-Training","created":"2023-12-05","cited_by_count":77},{"id":"2106.07760","title":"RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning","created":"2021-06-14","cited_by_count":74},{"id":"1901.01151","title":"Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision","created":"2019-01-03","cited_by_count":64},{"id":"2307.06290","title":"Instruction Mining: Instruction Data Selection for Tuning Large Language Models","created":"2023-07-12","cited_by_count":58},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29},{"id":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23},{"id":"2402.17327","title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","created":"2024-02-27","cited_by_count":15},{"id":"1709.02279","title":"Cynical Selection of Language Model Training Data","created":"2017-09-07","cited_by_count":13},{"id":"2410.16208","title":"Compute-Constrained Data Selection","created":"2024-10-21","cited_by_count":12},{"id":"2412.08832","title":"HadaCore: Tensor Core Accelerated Hadamard Transform Kernel","created":"2024-12-12","cited_by_count":12},{"id":"2005.00175","title":"Selecting Informative Contexts Improves Language Model Finetuning","created":"2020-05-01","cited_by_count":11},{"id":"2210.10951","title":"Automatic Document Selection for Efficient Encoder Pretraining","created":"2022-10-20","cited_by_count":11},{"id":"2412.00420","title":"TAROT: Targeted Data Selection via Optimal Transport","created":"2024-11-30","cited_by_count":9},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7},{"id":"2408.10419","title":"Second-Order Forward-Mode Automatic Differentiation for Optimization","created":"2024-08-19","cited_by_count":5}],"next_cursor":null}