{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"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":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"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":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2004.12265","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","created":"2020-04-26","cited_by_count":191},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"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":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"1901.03429","title":"On the Turing Completeness of Modern Neural Network Architectures","created":"2019-01-10","cited_by_count":129},{"id":"2311.00208","title":"What Formal Languages Can Transformers Express? A Survey","created":"2023-11-01","cited_by_count":124},{"id":"2312.03002","title":"The mechanistic basis of data dependence and abrupt learning in an in-context classification task","created":"2023-12-03","cited_by_count":118},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"2402.14735","title":"How Transformers Learn Causal Structure with Gradient Descent","created":"2024-02-22","cited_by_count":118},{"id":"2005.13407","title":"CausaLM: Causal Model Explanation Through Counterfactual Language Models","created":"2020-05-27","cited_by_count":117},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"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":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104},{"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":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100},{"id":"2204.06618","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","created":"2022-04-13","cited_by_count":93},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89},{"id":"2404.07129","title":"What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation","created":"2024-04-10","cited_by_count":89},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","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":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"2310.13897","title":"Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages","created":"2023-10-21","cited_by_count":49},{"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":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36},{"id":"2404.14994","title":"Transformers Can Represent $n$-gram Language Models","created":"2024-04-23","cited_by_count":32},{"id":"2406.14197","title":"On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning","created":"2024-06-20","cited_by_count":26},{"id":"2407.03310","title":"Universal Length Generalization with Turing Programs","created":"2024-07-03","cited_by_count":25},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17},{"id":"2305.16765","title":"Backpack Language Models","created":"2023-05-26","cited_by_count":15},{"id":"2406.04089","title":"On Limitation of Transformer for Learning HMMs","created":"2024-06-06","cited_by_count":10},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7}],"next_cursor":null}