{"list":"other","total":67,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"1711.09784","title":"Distilling a Neural Network Into a Soft Decision Tree","created":"2017-11-27","cited_by_count":236},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2207.08799","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","created":"2022-07-18","cited_by_count":187},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"2202.08658","title":"The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks","created":"2022-02-17","cited_by_count":142},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2312.13558","title":"The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction","created":"2023-12-21","cited_by_count":123},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63},{"id":"1710.06169","title":"Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation","created":"2017-10-17","cited_by_count":62},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62},{"id":"2310.19793","title":"On Learning Gaussian Multi-index Models with Gradient Flow","created":"2023-10-30","cited_by_count":57},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52},{"id":"1911.04974","title":"Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models","created":"2019-11-12","cited_by_count":42},{"id":"1706.09773","title":"Interpretability via Model Extraction","created":"2017-06-29","cited_by_count":40},{"id":"2107.09145","title":"Adaptive wavelet distillation from neural networks through interpretations","created":"2021-07-19","cited_by_count":32},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28},{"id":"2009.09435","title":"Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation","created":"2020-09-20","cited_by_count":25},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24},{"id":"2310.18780","title":"Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions","created":"2023-10-28","cited_by_count":24},{"id":"2109.00637","title":"Properly learning decision trees in almost polynomial time","created":"2021-09-01","cited_by_count":20},{"id":"2208.03113","title":"On the non-universality of deep learning: quantifying the cost of symmetry","created":"2022-08-05","cited_by_count":18},{"id":"1610.09036","title":"Interpreting Models via Single Tree Approximation","created":"2016-10-27","cited_by_count":17},{"id":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","cited_by_count":17},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","cited_by_count":15},{"id":"2309.03800","title":"Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck","created":"2023-09-07","cited_by_count":13},{"id":"1808.07573","title":"Approximation Trees: Statistical Stability in Model Distillation","created":"2018-08-22","cited_by_count":9},{"id":"2210.06375","title":"Superpolynomial Lower Bounds for Decision Tree Learning and Testing","created":"2022-10-12","cited_by_count":9},{"id":"1706.06934","title":"Exact Learning of Juntas from Membership Queries","created":"2017-06-21","cited_by_count":6},{"id":"1711.05195","title":"A learning problem that is independent of the set theory ZFC axioms","created":"2017-11-14","cited_by_count":5},{"id":"2307.04093","title":"Properly Learning Decision Trees with Queries Is NP-Hard","created":"2023-07-09","cited_by_count":5},{"id":"2211.12631","title":"A Generic Approach for Reproducible Model Distillation","created":"2022-11-22","cited_by_count":3}],"next_cursor":null}