{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"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":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141},{"id":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102},{"id":"2410.11325","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","created":"2024-10-15","cited_by_count":90},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84},{"id":"2401.08190","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","created":"2024-01-16","cited_by_count":81},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61},{"id":"2506.11116","title":"Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models","created":"2025-06-09","cited_by_count":50},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36},{"id":"2108.05698","title":"Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data","created":"2021-08-11","cited_by_count":32},{"id":"2310.04752","title":"A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization","created":"2023-10-07","cited_by_count":24},{"id":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18},{"id":"2405.07780","title":"DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations","created":"2024-05-13","cited_by_count":15},{"id":"2306.05426","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","created":"2023-06-08","cited_by_count":13},{"id":"2305.09651","title":"Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation","created":"2023-05-16","cited_by_count":8},{"id":"2405.08019","title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","created":"2024-05-11","cited_by_count":3},{"id":"2405.13325","title":"DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying","created":"2024-05-22","cited_by_count":3},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2}],"next_cursor":null}