{"list":"other","total":99,"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":"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2303.14070","title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","created":"2023-03-24","cited_by_count":325},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","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":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80},{"id":"2312.11420","title":"Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning","created":"2023-12-18","cited_by_count":64},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64},{"id":"2405.19597","title":"SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors","created":"2024-05-30","cited_by_count":58},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57},{"id":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38},{"id":"2306.00477","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","created":"2023-06-01","cited_by_count":26},{"id":"2401.16405","title":"Scaling Sparse Fine-Tuning to Large Language Models","created":"2024-01-29","cited_by_count":26},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24},{"id":"2312.11875","title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","created":"2023-12-19","cited_by_count":21},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19},{"id":"2404.18466","title":"HFT: Half Fine-Tuning for Large Language Models","created":"2024-04-29","cited_by_count":18},{"id":"2502.02797","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","created":"2025-02-05","cited_by_count":16},{"id":"2502.17510","title":"Recurrent Knowledge Identification and Fusion for Language Model Continual Learning","created":"2025-02-22","cited_by_count":15},{"id":"2505.14826","title":"FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain","created":"2025-05-20","cited_by_count":15},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14},{"id":"2411.04425","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","created":"2024-11-07","cited_by_count":14},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14},{"id":"2501.13669","title":"How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization","created":"2025-01-23","cited_by_count":13},{"id":"2502.04380","title":"Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data","created":"2025-02-05","cited_by_count":13},{"id":"2502.14709","title":"Group-Level Data Selection for Efficient Pretraining","created":"2025-02-20","cited_by_count":13},{"id":"2506.04805","title":"Adaptive Preconditioners Trigger Loss Spikes in Adam","created":"2025-06-05","cited_by_count":13},{"id":"2509.08255","title":"Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning","created":"2025-09-10","cited_by_count":13},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12},{"id":"2411.02688","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","created":"2024-11-05","cited_by_count":11},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11},{"id":"2602.17835","title":"Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning","created":"2026-02-19","cited_by_count":10},{"id":"2411.10696","title":"HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization","created":"2024-11-16","cited_by_count":9},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9},{"id":"2507.20400","title":"Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions","created":"2025-07-27","cited_by_count":9},{"id":"2510.17847","title":"CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","created":"2025-10-11","cited_by_count":8},{"id":"2602.18584","title":"GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry","created":"2026-02-20","cited_by_count":8},{"id":"2210.04382","title":"Parameter-Efficient Tuning with Special Token Adaptation","created":"2022-10-10","cited_by_count":7},{"id":"2507.16178","title":"LLM Data Selection and Utilization via Dynamic Bi-level Optimization","created":"2025-07-22","cited_by_count":7},{"id":"2601.23155","title":"SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training","created":"2026-01-30","cited_by_count":7},{"id":"2310.13008","title":"DavIR: Data Selection via Implicit Reward for Large Language Models","created":"2023-10-16","cited_by_count":6},{"id":"2310.16776","title":"DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection","created":"2023-10-25","cited_by_count":6},{"id":"2407.01320","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","created":"2024-07-01","cited_by_count":6},{"id":"2505.20211","title":"PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection","created":"2025-05-26","cited_by_count":6},{"id":"2507.22872","title":"TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning","created":"2025-07-30","cited_by_count":6},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5},{"id":"2505.23724","title":"SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA","created":"2025-05-29","cited_by_count":5},{"id":"2511.08620","title":"Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM","created":"2025-11-07","cited_by_count":5},{"id":"2512.24265","title":"Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning","created":"2025-12-30","cited_by_count":5},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4},{"id":"2503.01843","title":"When Can You Get Away with Low Memory Adam?","created":"2025-03-03","cited_by_count":3},{"id":"2506.00495","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","created":"2025-05-31","cited_by_count":3},{"id":"2506.21374","title":"Pay Attention to Small Weights","created":"2025-06-26","cited_by_count":3},{"id":"2509.17688","title":"TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation","created":"2025-09-22","cited_by_count":3},{"id":"2510.00386","title":"Train on Validation (ToV): Fast data selection with applications to fine-tuning","created":"2025-10-01","cited_by_count":3},{"id":"2510.18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning","created":"2025-10-21","cited_by_count":3},{"id":"2511.01077","title":"AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs","created":"2025-11-02","cited_by_count":3},{"id":"2601.17921","title":"ShapLoRA: Allocation of Low-rank Adaption on Large Language Models via Shapley Value Inspired Importance Estimation","created":"2026-01-25","cited_by_count":3},{"id":"2602.07804","title":"Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models","created":"2026-02-08","cited_by_count":3},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3},{"id":"2505.19609","title":"Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling","created":"2025-05-26","cited_by_count":2},{"id":"2505.22120","title":"LoKI: Low-damage Knowledge Implanting of Large Language Models","created":"2025-05-28","cited_by_count":2},{"id":"2511.15375","title":"Parameter Importance-Driven Continual Learning for Foundation Models","created":"2025-11-19","cited_by_count":2},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2},{"id":"2603.09865","title":"GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection","created":"2026-03-10","cited_by_count":2},{"id":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","cited_by_count":1},{"id":"2509.17428","title":"QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models","created":"2025-09-22","cited_by_count":1}],"next_cursor":null}