{"total":18,"rows":[{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236,"area":null},{"id":"2204.10757","title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","created":"2022-04-22","cited_by_count":109,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82,"area":null},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49,"area":null},{"id":"2104.08685","title":"Linguistic Dependencies and Statistical Dependence","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2502.16849","title":"Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2211.16031","title":"Syntactic Substitutability as Unsupervised Dependency Syntax","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2504.08778","title":"From Tokens to Lattices: Emergent Lattice Structures in Language Models","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2310.16261","title":"The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2605.20105","title":"Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2110.08430","title":"Metadata Shaping: Natural Language Annotations for the Tail","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2204.02067","title":"Design considerations for a hierarchical semantic compositional framework for medical natural language understanding","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2310.15259","title":"Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2312.14966","title":"Dynamic Syntax Mapping: A New Approach to Unsupervised Syntax Parsing","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2401.12997","title":"Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion","created":"2024-01-19","cited_by_count":0,"area":null}],"next_cursor":null}