{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"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":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"1502.04759","title":"Coordinate Descent Algorithms","created":"2015-02-17","cited_by_count":219},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"2003.02395","title":"A Simple Convergence Proof of Adam and Adagrad","created":"2020-03-05","cited_by_count":171},{"id":"2306.09782","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","created":"2023-06-16","cited_by_count":134},{"id":"1812.11446","title":"Greedy Layerwise Learning Can Scale to ImageNet","created":"2018-12-29","cited_by_count":115},{"id":"2208.09632","title":"Adam Can Converge Without Any Modification On Update Rules","created":"2022-08-20","cited_by_count":114},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112},{"id":"2304.13972","title":"Convergence of Adam Under Relaxed Assumptions","created":"2023-04-27","cited_by_count":99},{"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":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82},{"id":"2310.13243","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","created":"2023-10-20","cited_by_count":44},{"id":"2003.02249","title":"jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models","created":"2020-03-04","cited_by_count":39},{"id":"2310.17998","title":"Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity","created":"2023-10-27","cited_by_count":38},{"id":"1305.4723","title":"On the Complexity Analysis of Randomized Block-Coordinate Descent Methods","created":"2013-05-21","cited_by_count":21},{"id":"1712.08859","title":"Let's Make Block Coordinate Descent Converge Faster: Faster Greedy Rules, Message-Passing, Active-Set Complexity, and Superlinear Convergence","created":"2017-12-23","cited_by_count":17},{"id":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12},{"id":"2212.05088","title":"Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization","created":"2022-12-09","cited_by_count":9},{"id":"1503.06387","title":"On the Efficiency of Random Permutation for ADMM and Coordinate Descent","created":"2015-03-22","cited_by_count":2},{"id":"1903.01786","title":"Managing Randomization in the Multi-Block Alternating Direction Method of Multipliers for Quadratic Optimization","created":"2019-03-05","cited_by_count":2},{"id":"2307.16754","title":"Block-Coordinate Methods and Restarting for Solving Extensive-Form Games","created":"2023-07-31","cited_by_count":1}],"next_cursor":null}