{"list":"other","total":61,"rows":[{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"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":"1906.01698","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","created":"2019-06-04","cited_by_count":120},{"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":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"2005.00561","title":"When BERT Plays the Lottery, All Tickets Are Winning","created":"2020-05-01","cited_by_count":114},{"id":"2004.14786","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","created":"2020-04-30","cited_by_count":109},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"1911.12246","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","created":"2019-11-27","cited_by_count":88},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86},{"id":"2006.09286","title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","created":"2020-06-16","cited_by_count":85},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2010.07515","title":"RNNs can generate bounded hierarchical languages with optimal memory","created":"2020-10-15","cited_by_count":59},{"id":"1906.01615","title":"Sequential Neural Networks as Automata","created":"2019-06-04","cited_by_count":54},{"id":"2010.04303","title":"How Can Self-Attention Networks Recognize Dyck-n Languages?","created":"2020-10-09","cited_by_count":51},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48},{"id":"1906.03648","title":"LSTM Networks Can Perform Dynamic Counting","created":"2019-06-09","cited_by_count":45},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15},{"id":"2105.08855","title":"Effective Attention Sheds Light On Interpretability","created":"2021-05-18","cited_by_count":11},{"id":"2210.03575","title":"Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models","created":"2022-10-07","cited_by_count":9},{"id":"1802.08545","title":"Unsupervised Grammar Induction with Depth-bounded PCFG","created":"2018-02-23","cited_by_count":8},{"id":"2011.10036","title":"On the Dynamics of Training Attention Models","created":"2020-11-19","cited_by_count":8},{"id":"2106.01580","title":"The Limitations of Limited Context for Constituency Parsing","created":"2021-06-03","cited_by_count":5},{"id":"2207.13018","title":"Is Attention Interpretation? A Quantitative Assessment On Sets","created":"2022-07-26","cited_by_count":4}],"next_cursor":null}