{"total":57,"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":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"area":null},{"id":"2111.06719","title":"On Transferability of Prompt Tuning for Natural Language Processing","created":"2021-11-12","cited_by_count":75,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"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":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55,"area":null},{"id":"2311.11077","title":"Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning","created":"2023-11-18","cited_by_count":53,"area":null},{"id":"2311.13534","title":"LM-Cocktail: Resilient Tuning of Language Models via Model Merging","created":"2023-11-22","cited_by_count":44,"area":null},{"id":"2203.04640","title":"Memory Efficient Continual Learning with Transformers","created":"2022-03-09","cited_by_count":43,"area":null},{"id":"2304.14381","title":"$\\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation","created":"2023-04-27","cited_by_count":40,"area":null},{"id":"2109.06050","title":"Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training","created":"2021-09-13","cited_by_count":28,"area":null},{"id":"2109.00720","title":"LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting","created":"2021-08-31","cited_by_count":27,"area":null},{"id":"2210.14102","title":"Exploring Mode Connectivity for Pre-trained Language Models","created":"2022-10-25","cited_by_count":26,"area":null},{"id":"2212.00196","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","created":"2022-12-01","cited_by_count":26,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"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":"2205.12148","title":"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer","created":"2022-05-24","cited_by_count":22,"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":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2205.02170","title":"Efficient Few-Shot Fine-Tuning for Opinion Summarization","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2406.12208","title":"Knowledge Fusion By Evolving Weights of Language Models","created":"2024-06-18","cited_by_count":16,"area":null},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2203.08442","title":"Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation","created":"2022-03-16","cited_by_count":14,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2212.09683","title":"Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments","created":"2022-12-19","cited_by_count":14,"area":null},{"id":"2305.13256","title":"TaskWeb: Selecting Better Source Tasks for Multi-task NLP","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2108.08103","title":"AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters","created":"2021-08-18","cited_by_count":8,"area":null},{"id":"2210.11705","title":"Efficiently Tuned Parameters are Task Embeddings","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2305.19228","title":"Unsupervised Melody-to-Lyric Generation","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2109.08607","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","created":"2021-09-17","cited_by_count":6,"area":null},{"id":"2404.16418","title":"Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2108.00356","title":"Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning","created":"2021-08-01","cited_by_count":5,"area":null},{"id":"2204.08875","title":"ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs","created":"2022-04-19","cited_by_count":5,"area":null},{"id":"2210.10293","title":"Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2601.06672","title":"Will it Merge? On The Causes of Model Mergeability","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2203.10484","title":"Hierarchical Inductive Transfer for Continual Dialogue Learning","created":"2022-03-20","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":"2210.14254","title":"Leveraging Open Data and Task Augmentation to Automated Behavioral Coding of Psychotherapy Conversations in Low-Resource Scenarios","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2310.01217","title":"ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2407.16245","title":"Exploring the Effectiveness and Consistency of Task Selection in Intermediate-Task Transfer Learning","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2501.03870","title":"Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2204.04980","title":"A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition","created":"2022-04-11","cited_by_count":1,"area":null},{"id":"2303.06911","title":"ViM: Vision Middleware for Unified Downstream Transferring","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2308.00528","title":"Unimodal Intermediate Training for Multimodal Meme Sentiment Classification","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2501.03783","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}