{"list":"other","total":79,"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":"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":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"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":"2109.00110","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","created":"2021-08-31","cited_by_count":391},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2210.12283","title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","created":"2022-10-21","cited_by_count":291},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2012.05876","title":"Neurosymbolic AI: The 3rd Wave","created":"2020-12-10","cited_by_count":255},{"id":"2103.09177","title":"Deep learning: a statistical viewpoint","created":"2021-03-16","cited_by_count":240},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2302.12433","title":"ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics","created":"2023-02-24","cited_by_count":192},{"id":"1802.01396","title":"To understand deep learning we need to understand kernel learning","created":"2018-02-05","cited_by_count":187},{"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":"2106.10165","title":"The Principles of Deep Learning Theory","created":"2021-06-18","cited_by_count":173},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"2302.03025","title":"A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations","created":"2023-02-06","cited_by_count":144},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"1805.04908","title":"On the Practical Computational Power of Finite Precision RNNs for Language Recognition","created":"2018-05-13","cited_by_count":117},{"id":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116},{"id":"2005.04511","title":"Finding Universal Grammatical Relations in Multilingual BERT","created":"2020-05-09","cited_by_count":110},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86},{"id":"2301.02679","title":"Grokking modular arithmetic","created":"2023-01-06","cited_by_count":83},{"id":"2104.01112","title":"NaturalProofs: Mathematical Theorem Proving in Natural Language","created":"2021-03-24","cited_by_count":81},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72},{"id":"2207.09238","title":"Formal Algorithms for Transformers","created":"2022-07-19","cited_by_count":72},{"id":"2302.07253","title":"Energy Transformer","created":"2023-02-14","cited_by_count":71},{"id":"2301.10743","title":"Tighter Bounds on the Expressivity of Transformer Encoders","created":"2023-01-25","cited_by_count":66},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41},{"id":"2306.06085","title":"Trapping LLM Hallucinations Using Tagged Context Prompts","created":"2023-06-09","cited_by_count":34},{"id":"1711.05408","title":"Recurrent Neural Networks as Weighted Language Recognizers","created":"2017-11-15","cited_by_count":30},{"id":"2106.07890","title":"An enriched category theory of language: from syntax to semantics","created":"2021-06-15","cited_by_count":22},{"id":"2004.06866","title":"On the Linguistic Capacity of Real-Time Counter Automata","created":"2020-04-15","cited_by_count":17},{"id":"2305.18278","title":"Mathematical Structure of Syntactic Merge","created":"2023-05-29","cited_by_count":17},{"id":"2109.11515","title":"Outlier-Robust Sparse Estimation via Non-Convex Optimization","created":"2021-09-23","cited_by_count":14},{"id":"2305.17311","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models","created":"2023-05-27","cited_by_count":12},{"id":"2302.02497","title":"High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors","created":"2023-02-05","cited_by_count":5},{"id":"2306.16573","title":"Finite-Sample Symmetric Mean Estimation with Fisher Information Rate","created":"2023-06-28","cited_by_count":5},{"id":"1605.04238","title":"Semantic Spaces","created":"2016-05-13","cited_by_count":2}],"next_cursor":null}