{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"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":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1803.07640","title":"AllenNLP: A Deep Semantic Natural Language Processing Platform","created":"2018-03-20","cited_by_count":347},{"id":"2011.01403","title":"Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning","created":"2020-11-03","cited_by_count":276},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1711.00740","title":"Learning to Represent Programs with Graphs","created":"2017-11-01","cited_by_count":220},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"1804.05392","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","created":"2018-04-15","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":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148},{"id":"2305.05465","title":"The emergence of clusters in self-attention dynamics","created":"2023-05-09","cited_by_count":140},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","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":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102},{"id":"1912.11637","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","created":"2019-12-25","cited_by_count":62},{"id":"2210.03588","title":"Understanding Transformer Memorization Recall Through Idioms","created":"2022-10-07","cited_by_count":62},{"id":"1904.09708","title":"Compositional generalization in a deep seq2seq model by separating syntax and semantics","created":"2019-04-22","cited_by_count":56},{"id":"2103.04350","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","created":"2021-03-07","cited_by_count":51},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43},{"id":"2507.16003","title":"Learning without training: The implicit dynamics of in-context learning","created":"2025-07-21","cited_by_count":43},{"id":"2103.01620","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","created":"2021-03-02","cited_by_count":40},{"id":"2210.13181","title":"The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative","created":"2022-10-24","cited_by_count":35},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35},{"id":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34},{"id":"2409.05448","title":"Representational Analysis of Binding in Language Models","created":"2024-09-09","cited_by_count":28},{"id":"2410.23819","title":"Weight decay induces low-rank attention layers","created":"2024-10-31","cited_by_count":27},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24},{"id":"2404.16367","title":"Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers","created":"2024-04-25","cited_by_count":24},{"id":"2505.20896","title":"How Do Transformers Learn Variable Binding in Symbolic Programs?","created":"2025-05-27","cited_by_count":21},{"id":"2104.07578","title":"Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models","created":"2021-04-15","cited_by_count":14},{"id":"2202.06521","title":"Source Code Summarization with Structural Relative Position Guided Transformer","created":"2022-02-14","cited_by_count":14},{"id":"1908.11522","title":"Parsing All: Syntax and Semantics, Dependencies and Spans","created":"2019-08-30","cited_by_count":13},{"id":"2010.10998","title":"Open-Domain Frame Semantic Parsing Using Transformers","created":"2020-10-21","cited_by_count":12},{"id":"2205.05943","title":"Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs","created":"2022-05-12","cited_by_count":3},{"id":"2601.19208","title":"How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability","created":"2026-01-27","cited_by_count":3},{"id":"2512.14709","title":"Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning","created":"2025-12-08","cited_by_count":2}],"next_cursor":null}