{"list":"other","total":54,"rows":[{"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"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":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"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":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203},{"id":"1811.09720","title":"Representer Point Selection for Explaining Deep Neural Networks","created":"2018-11-23","cited_by_count":187},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2306.08018","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","created":"2023-06-13","cited_by_count":133},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"2012.15781","title":"FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging","created":"2020-12-31","cited_by_count":120},{"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":"2311.15653","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","created":"2023-11-27","cited_by_count":107},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77},{"id":"2310.10049","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","created":"2023-10-16","cited_by_count":63},{"id":"2204.04677","title":"FedCorr: Multi-Stage Federated Learning for Label Noise Correction","created":"2022-04-10","cited_by_count":61},{"id":"2305.09246","title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning","created":"2023-05-16","cited_by_count":58},{"id":"2311.08182","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","created":"2023-11-14","cited_by_count":52},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43},{"id":"2012.01700","title":"Robust Federated Learning with Noisy Labels","created":"2020-12-03","cited_by_count":40},{"id":"2402.16705","title":"SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection","created":"2024-02-26","cited_by_count":34},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31},{"id":"2207.06814","title":"BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling","created":"2022-07-14","cited_by_count":30},{"id":"2406.04845","title":"FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models","created":"2024-06-07","cited_by_count":30},{"id":"2205.10110","title":"FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels","created":"2022-05-20","cited_by_count":12},{"id":"2304.02892","title":"Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients","created":"2023-04-06","cited_by_count":12},{"id":"2312.10324","title":"Federated Learning with Instance-Dependent Noisy Label","created":"2023-12-16","cited_by_count":9},{"id":"2409.07136","title":"Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models","created":"2024-09-11","cited_by_count":2}],"next_cursor":null}