{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"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":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2410.01560","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","created":"2024-10-02","cited_by_count":200},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2005.00628","title":"Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?","created":"2020-05-01","cited_by_count":127},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72},{"id":"2504.00698","title":"Command A: An Enterprise-Ready Large Language Model","created":"2025-04-01","cited_by_count":59},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2304.14381","title":"$\\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation","created":"2023-04-27","cited_by_count":40},{"id":"1906.03890","title":"Automatically Identifying Complaints in Social Media","created":"2019-06-10","cited_by_count":25},{"id":"2503.10633","title":"We Should Chart an Atlas of All the World's Models","created":"2025-03-13","cited_by_count":25},{"id":"2303.14957","title":"unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network","created":"2023-03-27","cited_by_count":24},{"id":"2103.11909","title":"Identifying Machine-Paraphrased Plagiarism","created":"2021-03-22","cited_by_count":16},{"id":"2405.13053","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","created":"2024-05-19","cited_by_count":16},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","cited_by_count":12},{"id":"2506.13234","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","created":"2025-06-16","cited_by_count":9},{"id":"2411.02207","title":"Collective Model Intelligence Requires Compatible Specialization","created":"2024-11-04","cited_by_count":7},{"id":"2511.06346","title":"LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation","created":"2025-11-09","cited_by_count":4},{"id":"2512.24991","title":"Efficiently Estimating Data Efficiency for Language Model Fine-tuning","created":"2025-12-31","cited_by_count":1}],"next_cursor":null}