{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"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":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2401.10774","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","created":"2024-01-19","cited_by_count":843},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"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":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176},{"id":"2402.16837","title":"Do Large Language Models Latently Perform Multi-Hop Reasoning?","created":"2024-02-26","cited_by_count":169},{"id":"1912.13283","title":"oLMpics -- On what Language Model Pre-training Captures","created":"2019-12-31","cited_by_count":161},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113},{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85},{"id":"2303.11873","title":"A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks","created":"2023-03-21","cited_by_count":83},{"id":"2203.08383","title":"Iteratively Prompt Pre-trained Language Models for Chain of Thought","created":"2022-03-16","cited_by_count":75},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65},{"id":"2305.18741","title":"Grokking of Hierarchical Structure in Vanilla Transformers","created":"2023-05-30","cited_by_count":53},{"id":"2303.06173","title":"Unifying Grokking and Double Descent","created":"2023-03-10","cited_by_count":50},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49},{"id":"2212.01349","title":"Nonparametric Masked Language Modeling","created":"2022-12-02","cited_by_count":40},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","cited_by_count":35},{"id":"2310.07096","title":"Sparse Universal Transformer","created":"2023-10-11","cited_by_count":32},{"id":"2401.10463","title":"Critical Data Size of Language Models from a Grokking Perspective","created":"2024-01-19","cited_by_count":24},{"id":"2402.15175","title":"Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition","created":"2024-02-23","cited_by_count":23},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15}],"next_cursor":null}