{"total":162,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"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":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164,"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":"2109.14739","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","created":"2021-09-29","cited_by_count":139,"area":null},{"id":"2211.13308","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","created":"2022-11-23","cited_by_count":129,"area":null},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"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":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"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":"2109.05729","title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation","created":"2021-09-13","cited_by_count":81,"area":null},{"id":"2305.06090","title":"XTab: Cross-table Pretraining for Tabular Transformers","created":"2023-05-10","cited_by_count":81,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","cited_by_count":57,"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":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2107.13602","title":"Domain-matched Pre-training Tasks for Dense Retrieval","created":"2021-07-28","cited_by_count":53,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46,"area":null},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","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":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2208.09770","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","created":"2022-08-21","cited_by_count":29,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27,"area":null},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26,"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":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23,"area":null},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2203.08985","title":"Label Semantics for Few Shot Named Entity Recognition","created":"2022-03-16","cited_by_count":21,"area":null},{"id":"2302.07730","title":"Transformer models: an introduction and catalog","created":"2023-02-12","cited_by_count":21,"area":null},{"id":"2309.09500","title":"PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction","created":"2023-09-18","cited_by_count":20,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2201.05222","title":"Assemble Foundation Models for Automatic Code Summarization","created":"2022-01-13","cited_by_count":17,"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":"2212.10449","title":"Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization","created":"2022-12-20","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":"2104.08620","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","created":"2021-04-17","cited_by_count":16,"area":null},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"area":null},{"id":"2410.01109","title":"Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2410.20008","title":"Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Language Models","created":"2024-10-25","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":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2110.07731","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","created":"2021-10-14","cited_by_count":13,"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":"2403.16056","title":"Qibo: A Large Language Model for Traditional Chinese Medicine","created":"2024-03-24","cited_by_count":13,"area":null},{"id":"2410.06741","title":"CoBa: Convergence Balancer for Multitask Finetuning of Large Language Models","created":"2024-10-09","cited_by_count":13,"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":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12,"area":null},{"id":"2205.14521","title":"Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization","created":"2022-05-28","cited_by_count":12,"area":null},{"id":"2302.09042","title":"Privately Customizing Prefinetuning to Better Match User Data in Federated Learning","created":"2023-02-17","cited_by_count":12,"area":null},{"id":"2311.10418","title":"DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines","created":"2023-11-17","cited_by_count":12,"area":null},{"id":"2401.10040","title":"Large Language Models for Scientific Information Extraction: An Empirical Study for Virology","created":"2024-01-18","cited_by_count":12,"area":null},{"id":"2109.13620","title":"Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking","created":"2021-09-28","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":"2410.15661","title":"Scalable Data Ablation Approximations for Language Models through Modular Training and Merging","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2107.05295","title":"DaCy: A Unified Framework for Danish NLP","created":"2021-07-12","cited_by_count":10,"area":null},{"id":"2203.03312","title":"SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding","created":"2022-03-07","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":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2204.07142","title":"CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations","created":"2022-04-14","cited_by_count":9,"area":null},{"id":"2205.09178","title":"PreQuEL: Quality Estimation of Machine Translation Outputs in Advance","created":"2022-05-18","cited_by_count":9,"area":null},{"id":"2205.09898","title":"Let the Model Decide its Curriculum for Multitask Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2307.02729","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"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":"2211.00243","title":"Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection","created":"2022-11-01","cited_by_count":7,"area":null},{"id":"2305.05816","title":"Best-Effort Adaptation","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7,"area":null},{"id":"2511.07074","title":"Importance-Aware Data Selection for Efficient LLM Instruction Tuning","created":"2025-11-10","cited_by_count":7,"area":null},{"id":"2104.14860","title":"Summarization, Simplification, and Generation: The Case of Patents","created":"2021-04-30","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":"2204.07834","title":"Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding","created":"2022-04-16","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":"2310.11670","title":"Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2402.17493","title":"The Foundational Capabilities of Large Language Models in Predicting Postoperative Risks Using Clinical Notes","created":"2024-02-27","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":"2210.01425","title":"Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2212.09278","title":"MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2303.09421","title":"SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2305.08152","title":"STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation","created":"2023-05-14","cited_by_count":5,"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}],"next_cursor":"100"}