{"list":"other","total":50,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2402.07871","title":"Scaling Laws for Fine-Grained Mixture of Experts","created":"2024-02-12","cited_by_count":173},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144},{"id":"1907.05242","title":"Large Memory Layers with Product Keys","created":"2019-07-10","cited_by_count":124},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57},{"id":"2406.16437","title":"Theory on Mixture-of-Experts in Continual Learning","created":"2024-06-24","cited_by_count":54},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48},{"id":"2404.05567","title":"Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models","created":"2024-04-08","cited_by_count":42},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17},{"id":"2305.16765","title":"Backpack Language Models","created":"2023-05-26","cited_by_count":15},{"id":"2311.10768","title":"Memory Augmented Language Models through Mixture of Word Experts","created":"2023-11-15","cited_by_count":9}],"next_cursor":null}