{"total":14,"rows":[{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2404.09562","title":"{\\sigma}-GPTs: A New Approach to Autoregressive Models","created":"2024-04-15","cited_by_count":20,"area":null},{"id":"2410.23506","title":"The Belief State Transformer","created":"2024-10-30","cited_by_count":12,"area":null},{"id":"2508.09654","title":"Improving Diversity in Language Models: When Temperature Fails, Change the Loss","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2506.06832","title":"Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2411.11061","title":"Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text","created":"2024-11-17","cited_by_count":1,"area":null},{"id":"2504.17069","title":"Distilling Specialized Orders for Visual Generation","created":"2025-04-23","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":"2603.10074","title":"Marginals Before Conditionals","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2511.19997","title":"Directional Optimization Asymmetry in Transformers: A Synthetic Stress Test","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2606.14943","title":"Simplifying the Modeling of Arbitrary Conditionals in Natural Language","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.27881","title":"A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.07129","title":"Line-Coupled Language Model","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}