{"total":128,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"area":null},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"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":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"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":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2211.12485","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","created":"2022-11-22","cited_by_count":46,"area":null},{"id":"2203.04640","title":"Memory Efficient Continual Learning with Transformers","created":"2022-03-09","cited_by_count":43,"area":null},{"id":"2204.07937","title":"Unsupervised Cross-Task Generalization via Retrieval Augmentation","created":"2022-04-17","cited_by_count":42,"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":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36,"area":"synth"},{"id":"2106.05426","title":"Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses","created":"2021-06-09","cited_by_count":34,"area":null},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34,"area":null},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"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":"2310.19975","title":"BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing","created":"2023-10-30","cited_by_count":25,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","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":"2303.14582","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","created":"2023-03-25","cited_by_count":20,"area":null},{"id":"2409.06091","title":"Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity","created":"2024-09-09","cited_by_count":20,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2108.11696","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2204.11117","title":"Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning","created":"2022-04-23","cited_by_count":17,"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":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2306.14009","title":"Boosting Multitask Learning on Graphs through Higher-Order Task Affinities","created":"2023-06-24","cited_by_count":15,"area":null},{"id":"2203.08565","title":"Geographic Adaptation of Pretrained Language Models","created":"2022-03-16","cited_by_count":14,"area":null},{"id":"2406.20030","title":"LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models","created":"2024-06-28","cited_by_count":14,"area":"moe"},{"id":"2505.03793","title":"LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","cited_by_count":13,"area":null},{"id":"2409.19458","title":"Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach","created":"2024-09-28","cited_by_count":13,"area":null},{"id":"2104.08840","title":"On the Influence of Masking Policies in Intermediate Pre-training","created":"2021-04-18","cited_by_count":12,"area":null},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2310.17514","title":"The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks","created":"2023-10-26","cited_by_count":12,"area":null},{"id":"2104.08078","title":"To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2104.12567","title":"Evaluating the Values of Sources in Transfer Learning","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2205.06262","title":"FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue","created":"2022-05-12","cited_by_count":11,"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":"2205.03815","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","created":"2022-05-08","cited_by_count":10,"area":null},{"id":"2305.09025","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2201.11576","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","created":"2022-01-27","cited_by_count":8,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2205.01886","title":"P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2210.11255","title":"Evidence > Intuition: Transferability Estimation for Encoder Selection","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2210.11705","title":"Efficiently Tuned Parameters are Task Embeddings","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2308.06610","title":"Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation","created":"2023-08-12","cited_by_count":7,"area":null},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"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":"2111.01340","title":"Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2111.05013","title":"Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks","created":"2021-11-09","cited_by_count":6,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","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":"2305.14007","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2107.09931","title":"The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2107.11954","title":"Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2109.00475","title":"Capturing Stance Dynamics in Social Media: Open Challenges and Research Directions","created":"2021-09-01","cited_by_count":4,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2310.15541","title":"Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2312.04775","title":"How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey","created":"2023-12-08","cited_by_count":4,"area":null},{"id":"2406.11721","title":"The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2409.19680","title":"Instruction Embedding: Latent Representations of Instructions Towards Task Identification","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2410.12774","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2410.13804","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2111.03628","title":"Exploiting a Zoo of Checkpoints for Unseen Tasks","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2112.05647","title":"Analysis and Prediction of NLP Models Via Task Embeddings","created":"2021-12-10","cited_by_count":3,"area":null},{"id":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2105.14809","title":"Transfer Learning for Sequence Generation: from Single-source to Multi-source","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2112.15051","title":"Does QA-based intermediate training help fine-tuning language models for text classification?","created":"2021-12-30","cited_by_count":2,"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":"2305.14569","title":"Few-shot Unified Question Answering: Tuning Models or Prompts?","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2402.14522","title":"Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond","created":"2024-02-22","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":"2408.13227","title":"Enhancing Few-Shot Transfer Learning with Optimized Multi-Task Prompt Tuning through Modular Prompt Composition","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2408.14677","title":"Can Optimization Trajectories Explain Multi-Task Transfer?","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2409.18446","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","created":"2024-09-27","cited_by_count":2,"area":null}],"next_cursor":"100"}