{"list":"other","total":52,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"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":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2310.05492","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","created":"2023-10-09","cited_by_count":223},{"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":"2407.01492","title":"RegMix: Data Mixture as Regression for Language Model Pre-training","created":"2024-07-01","cited_by_count":177},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109},{"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":"2310.08433","title":"A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing","created":"2023-10-12","cited_by_count":99},{"id":"2310.15393","title":"DoGE: Domain Reweighting with Generalization Estimation","created":"2023-10-23","cited_by_count":90},{"id":"2211.05994","title":"A Survey of Knowledge Enhanced Pre-trained Language Models","created":"2022-11-11","cited_by_count":76},{"id":"2404.00213","title":"Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning","created":"2024-03-30","cited_by_count":58},{"id":"2304.00008","title":"On the Creativity of Large Language Models","created":"2023-03-27","cited_by_count":57},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38},{"id":"2402.06094","title":"Rethinking Data Selection for Supervised Fine-Tuning","created":"2024-02-08","cited_by_count":35},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34},{"id":"2409.16986","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","created":"2024-09-25","cited_by_count":34},{"id":"2402.10430","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models","created":"2024-02-16","cited_by_count":32},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31},{"id":"2503.16212","title":"MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion","created":"2025-03-20","cited_by_count":30},{"id":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27},{"id":"2402.14526","title":"Balanced Data Sampling for Language Model Training with Clustering","created":"2024-02-22","cited_by_count":23},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21},{"id":"2411.04425","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","created":"2024-11-07","cited_by_count":14},{"id":"2402.14270","title":"Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization","created":"2024-02-22","cited_by_count":12},{"id":"2407.06380","title":"Data, Data Everywhere: A Guide for Pretraining Dataset Construction","created":"2024-07-08","cited_by_count":11},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11},{"id":"2504.20644","title":"Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection","created":"2025-04-29","cited_by_count":5}],"next_cursor":null}