{"list":"other","total":51,"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":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"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":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"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":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"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":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1901.06523","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","created":"2019-01-19","cited_by_count":368},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"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":"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":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75},{"id":"2402.19442","title":"Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality","created":"2024-02-29","cited_by_count":74},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73},{"id":"2204.08292","title":"StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts","created":"2022-04-18","cited_by_count":68},{"id":"2007.07497","title":"Phase diagram for two-layer ReLU neural networks at infinite-width limit","created":"2020-07-15","cited_by_count":67},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59},{"id":"2002.08404","title":"Implicit Regularization of Random Feature Models","created":"2020-02-19","cited_by_count":54},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49},{"id":"2402.14328","title":"Understanding and Patching Compositional Reasoning in LLMs","created":"2024-02-22","cited_by_count":46},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24},{"id":"2402.03268","title":"Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation","created":"2024-02-05","cited_by_count":22},{"id":"2404.01601","title":"What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks","created":"2024-04-02","cited_by_count":19},{"id":"2205.12101","title":"Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width","created":"2022-05-24","cited_by_count":17},{"id":"2205.13647","title":"Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures","created":"2022-05-26","cited_by_count":17},{"id":"2207.14000","title":"Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation","created":"2022-07-28","cited_by_count":15},{"id":"2203.15099","title":"LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models","created":"2022-03-28","cited_by_count":12},{"id":"2401.11600","title":"Understanding the Generalization Benefits of Late Learning Rate Decay","created":"2024-01-21","cited_by_count":6}],"next_cursor":null}