{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437},{"id":"2308.14761","title":"Unified Concept Editing in Diffusion Models","created":"2023-08-25","cited_by_count":388},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"1910.08485","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","created":"2019-10-18","cited_by_count":259},{"id":"1411.5908","title":"Understanding image representations by measuring their equivariance and equivalence","created":"2014-11-21","cited_by_count":243},{"id":"2012.00363","title":"Modifying Memories in Transformer Models","created":"2020-12-01","cited_by_count":224},{"id":"1911.02549","title":"MLPerf Inference Benchmark","created":"2019-11-06","cited_by_count":199},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192},{"id":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2004.00584","title":"Deep Entity Matching with Pre-Trained Language Models","created":"2020-04-01","cited_by_count":144},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"1502.04269","title":"Supersparse Linear Integer Models for Optimized Medical Scoring Systems","created":"2015-02-15","cited_by_count":76},{"id":"2110.07356","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","created":"2021-09-09","cited_by_count":76},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48},{"id":"2311.09538","title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","created":"2023-11-16","cited_by_count":47},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38},{"id":"2210.01922","title":"Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning","created":"2022-10-04","cited_by_count":38},{"id":"1901.00735","title":"Dataset search: a survey","created":"2019-01-03","cited_by_count":36},{"id":"2209.13589","title":"SANTOS: Relationship-based Semantic Table Union Search","created":"2022-09-27","cited_by_count":32},{"id":"2011.10427","title":"Dataset Discovery in Data Lakes","created":"2020-11-20","cited_by_count":31},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26},{"id":"1603.07410","title":"LSH Ensemble: Internet-Scale Domain Search","created":"2016-03-24","cited_by_count":24},{"id":"2402.05160","title":"What's documented in AI? Systematic Analysis of 32K AI Model Cards","created":"2024-02-07","cited_by_count":11},{"id":"2107.11152","title":"On data lake architectures and metadata management","created":"2021-07-23","cited_by_count":8}],"next_cursor":null}