{"list":"other","total":53,"rows":[{"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":"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"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":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2405.10938","title":"Observational Scaling Laws and the Predictability of Language Model Performance","created":"2024-05-17","cited_by_count":130},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94},{"id":"2309.16298","title":"At Which Training Stage Does Code Data Help LLMs Reasoning?","created":"2023-09-28","cited_by_count":82},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47},{"id":"2409.05816","title":"Improving Pretraining Data Using Perplexity Correlations","created":"2024-09-09","cited_by_count":46},{"id":"2504.11393","title":"DataDecide: How to Predict Best Pretraining Data with Small Experiments","created":"2025-04-15","cited_by_count":40},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39},{"id":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34},{"id":"2401.09181","title":"Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer","created":"2024-01-17","cited_by_count":31},{"id":"2405.21068","title":"Code Pretraining Improves Entity Tracking Abilities of Language Models","created":"2024-05-31","cited_by_count":31},{"id":"2410.11840","title":"A Hitchhiker's Guide to Scaling Law Estimation","created":"2024-10-15","cited_by_count":27},{"id":"2407.17467","title":"CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models","created":"2024-07-24","cited_by_count":23},{"id":"2407.20177","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","created":"2024-07-29","cited_by_count":22},{"id":"2510.22037","title":"ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality","created":"2025-10-24","cited_by_count":22},{"id":"2410.15035","title":"Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging","created":"2024-10-19","cited_by_count":14},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13},{"id":"2410.02229","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","created":"2024-10-03","cited_by_count":10},{"id":"2506.14111","title":"Essential-Web v1.0: 24T tokens of organized web data","created":"2025-06-17","cited_by_count":8},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7},{"id":"2509.24012","title":"Pretraining Scaling Laws for Generative Evaluations of Language Models","created":"2025-09-28","cited_by_count":5},{"id":"2506.10378","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","created":"2025-06-12","cited_by_count":4},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","cited_by_count":3}],"next_cursor":null}