{"list":"other","total":62,"rows":[{"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":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"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":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"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":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2305.12474","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","created":"2023-05-21","cited_by_count":186},{"id":"2403.16952","title":"Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance","created":"2024-03-25","cited_by_count":184},{"id":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2403.02884","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","created":"2024-03-05","cited_by_count":144},{"id":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105},{"id":"2306.16636","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","created":"2023-06-29","cited_by_count":90},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80},{"id":"2410.06526","title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks","created":"2024-10-09","cited_by_count":70},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52},{"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":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34},{"id":"2510.22115","title":"Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation","created":"2025-10-25","cited_by_count":34},{"id":"2507.00885","title":"Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check","created":"2025-07-01","cited_by_count":29},{"id":"2405.14908","title":"BiMix: A Bivariate Data Mixing Law for Language Model Pretraining","created":"2024-05-23","cited_by_count":25},{"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":"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":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11},{"id":"2502.10510","title":"MixMin: Finding Data Mixtures via Convex Minimization","created":"2025-02-14","cited_by_count":11},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9},{"id":"2505.16066","title":"Merge to Mix: Mixing Datasets via Model Merging","created":"2025-05-21","cited_by_count":7},{"id":"2412.04144","title":"If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs","created":"2024-12-05","cited_by_count":6},{"id":"2502.15950","title":"Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models","created":"2025-02-21","cited_by_count":5},{"id":"2508.11551","title":"ADMIRE-BayesOpt: Accelerated Data MIxture RE-weighting for Language Models with Bayesian Optimization","created":"2025-08-15","cited_by_count":5},{"id":"2511.13254","title":"Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance","created":"2025-11-17","cited_by_count":4},{"id":"2510.09295","title":"MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics","created":"2025-10-10","cited_by_count":1}],"next_cursor":null}