{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"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":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"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":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264},{"id":"2206.02336","title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","created":"2022-06-06","cited_by_count":233},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2308.07317","title":"Platypus: Quick, Cheap, and Powerful Refinement of LLMs","created":"2023-08-14","cited_by_count":150},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84},{"id":"2109.03034","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","created":"2021-09-07","cited_by_count":82},{"id":"1706.00359","title":"Discovering Discrete Latent Topics with Neural Variational Inference","created":"2017-06-01","cited_by_count":79},{"id":"1704.06363","title":"Hard Mixtures of Experts for Large Scale Weakly Supervised Vision","created":"2017-04-20","cited_by_count":67},{"id":"2112.08348","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","created":"2021-12-15","cited_by_count":64},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60},{"id":"1711.05411","title":"Z-Forcing: Training Stochastic Recurrent Networks","created":"2017-11-15","cited_by_count":51},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32},{"id":"2306.00784","title":"Interpretable Math Word Problem Solution Generation Via Step-by-step Planning","created":"2023-06-01","cited_by_count":17},{"id":"2305.03796","title":"Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation","created":"2023-05-05","cited_by_count":13}],"next_cursor":null}