{"list":"other","total":54,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150},{"id":"2110.01799","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","created":"2021-10-05","cited_by_count":148},{"id":"2306.14050","title":"Symbolic Chain-of-Thought Distillation: Small Models Can Also \"Think\" Step-by-Step","created":"2023-06-24","cited_by_count":148},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"1709.01848","title":"Depression and Self-Harm Risk Assessment in Online Forums","created":"2017-09-06","cited_by_count":84},{"id":"2009.04202","title":"Impact of News on the Commodity Market: Dataset and Results","created":"2020-09-09","cited_by_count":80},{"id":"1911.00841","title":"Question Answering for Privacy Policies: Combining Computational and Legal Perspectives","created":"2019-11-03","cited_by_count":67},{"id":"2009.10685","title":"Tensor Programs III: Neural Matrix Laws","created":"2020-09-22","cited_by_count":49},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38},{"id":"2410.07064","title":"Data Selection via Optimal Control for Language Models","created":"2024-10-09","cited_by_count":38},{"id":"2502.06042","title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","created":"2025-02-09","cited_by_count":35},{"id":"2408.11857","title":"Hermes 3 Technical Report","created":"2024-08-15","cited_by_count":34},{"id":"2206.12543","title":"A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel","created":"2022-06-25","cited_by_count":30},{"id":"2405.12915","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","created":"2024-05-21","cited_by_count":30},{"id":"2407.15235","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","created":"2024-07-21","cited_by_count":30},{"id":"2410.11303","title":"TSDS: Data Selection for Task-Specific Model Finetuning","created":"2024-10-15","cited_by_count":28},{"id":"2410.16701","title":"ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models","created":"2024-10-22","cited_by_count":21},{"id":"2306.00458","title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity","created":"2023-06-01","cited_by_count":17},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15},{"id":"2305.19358","title":"Stable Anisotropic Regularization","created":"2023-05-30","cited_by_count":12},{"id":"2405.20192","title":"TAIA: Large Language Models are Out-of-Distribution Data Learners","created":"2024-05-30","cited_by_count":8},{"id":"2407.13331","title":"Reconstruct the Pruned Model without Any Retraining","created":"2024-07-18","cited_by_count":4},{"id":"2505.11564","title":"HessFormer: Hessians at Foundation Scale","created":"2025-05-16","cited_by_count":4},{"id":"2211.08794","title":"Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations","created":"2022-11-16","cited_by_count":3},{"id":"2506.08764","title":"On the Stability of the Jacobian Matrix in Deep Neural Networks","created":"2025-06-10","cited_by_count":3},{"id":"2408.08669","title":"HSDreport: Heart Sound Diagnosis with Echocardiography Reports","created":"2024-08-16","cited_by_count":1}],"next_cursor":null}