{"total":17,"rows":[{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"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":"2310.02396","title":"Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse","created":"2023-10-03","cited_by_count":9,"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":"2209.08966","title":"Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2212.10929","title":"SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning","created":"2022-12-21","cited_by_count":5,"area":null},{"id":"2305.07393","title":"Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2305.09946","title":"AdaMSS: Adaptive Multi-Modality Segmentation-to-Survival Learning for Survival Outcome Prediction from PET/CT Images","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2501.03863","title":"Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study","created":"2025-01-07","cited_by_count":3,"area":null},{"id":"2506.09093","title":"Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data","created":"2025-06-10","cited_by_count":3,"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":"2310.10955","title":"A State-Vector Framework for Dataset Effects","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2305.12671","title":"Transferring Fairness using Multi-Task Learning with Limited Demographic Information","created":"2023-05-22","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}],"next_cursor":null}