{"total":18,"rows":[{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23,"area":null},{"id":"2205.08124","title":"When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning","created":"2022-05-17","cited_by_count":17,"area":null},{"id":"2306.12916","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2405.04163","title":"MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization","created":"2024-05-07","cited_by_count":8,"area":null},{"id":"2209.11102","title":"Scope of Pre-trained Language Models for Detecting Conflicting Health Information","created":"2022-09-22","cited_by_count":4,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2509.13624","title":"Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2303.06911","title":"ViM: Vision Middleware for Unified Downstream Transferring","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2312.06053","title":"IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2201.12407","title":"Schema-Free Dependency Parsing via Sequence Generation","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2212.05039","title":"Incorporating Emotions into Health Mention Classification Task on Social Media","created":"2022-12-09","cited_by_count":0,"area":null},{"id":"2306.16125","title":"A Framework for Identifying Depression on Social Media: MentalRiskES@IberLEF 2023","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2402.17608","title":"Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2504.21685","title":"Enhancing Health Mention Classification Performance: A Study on Advancements in Parameter Efficient Tuning","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2512.03862","title":"Diminishing Returns in Self-Supervised Learning","created":"2025-12-03","cited_by_count":0,"area":null}],"next_cursor":null}