{"list":"other","total":53,"rows":[{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"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":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"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":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2502.02737","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","created":"2025-02-04","cited_by_count":335},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160},{"id":"2310.06786","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","created":"2023-10-10","cited_by_count":155},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2310.19341","title":"Skywork: A More Open Bilingual Foundation Model","created":"2023-10-30","cited_by_count":112},{"id":"2406.08446","title":"OLMES: A Standard for Language Model Evaluations","created":"2024-06-12","cited_by_count":106},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104},{"id":"2502.10341","title":"Organize the Web: Constructing Domains Enhances Pre-Training Data Curation","created":"2025-02-14","cited_by_count":76},{"id":"2012.00413","title":"CPM: A Large-scale Generative Chinese Pre-trained Language Model","created":"2020-12-01","cited_by_count":60},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52},{"id":"2308.10755","title":"WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models","created":"2023-08-21","cited_by_count":50},{"id":"2407.13773","title":"OpenDataLab: Empowering General Artificial Intelligence with Open Datasets","created":"2024-06-04","cited_by_count":29},{"id":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23},{"id":"2501.08197","title":"OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training","created":"2025-01-14","cited_by_count":21},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21},{"id":"2511.13421","title":"Larger Datasets Can Be Repeated More: A Theoretical Analysis of Multi-Epoch Scaling in Linear Regression","created":"2025-11-17","cited_by_count":16},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7}],"next_cursor":null}