{"total":20,"rows":[{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143,"area":null},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2401.17505","title":"Arrows of Time for Large Language Models","created":"2024-01-30","cited_by_count":20,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2410.23506","title":"The Belief State Transformer","created":"2024-10-30","cited_by_count":12,"area":null},{"id":"2502.06901","title":"Enabling Autoregressive Models to Fill In Masked Tokens","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2405.17103","title":"Empowering Character-level Text Infilling by Eliminating Sub-Tokens","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2501.08648","title":"MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities","created":"2025-01-15","cited_by_count":5,"area":null},{"id":"2606.16246","title":"Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2311.17972","title":"Self-Infilling Code Generation","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2410.09817","title":"Reverse Modeling in Large Language Models","created":"2024-10-13","cited_by_count":2,"area":null},{"id":"2508.00374","title":"Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2401.02450","title":"Locally Differentially Private Embedding Models in Distributed Fraud Prevention Systems","created":"2024-01-03","cited_by_count":1,"area":null},{"id":"2505.08739","title":"Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2505.18789","title":"From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2408.09640","title":"Acquiring Bidirectionality via Large and Small Language Models","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2609.07129","title":"Line-Coupled Language Model","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}