{"total":323,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906,"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":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314,"area":null},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288,"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":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252,"area":null},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192,"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":"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":"2211.13308","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","created":"2022-11-23","cited_by_count":129,"area":null},{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"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":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86,"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":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79,"area":null},{"id":"2103.00242","title":"A Survey on Stance Detection for Mis- and Disinformation Identification","created":"2021-02-27","cited_by_count":75,"area":null},{"id":"2305.19000","title":"Independent Component Alignment for Multi-Task Learning","created":"2023-05-30","cited_by_count":70,"area":null},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67,"area":null},{"id":"2106.16038","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","created":"2021-06-30","cited_by_count":65,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2109.11427","title":"Automated Fact-Checking: A Survey","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2106.03427","title":"Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring","created":"2021-06-07","cited_by_count":53,"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":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"area":null},{"id":"2101.00117","title":"Multi-task Retrieval for Knowledge-Intensive Tasks","created":"2021-01-01","cited_by_count":44,"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":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41,"area":null},{"id":"2111.06685","title":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","created":"2021-11-12","cited_by_count":37,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37,"area":null},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35,"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":"2305.13225","title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","created":"2023-05-22","cited_by_count":33,"area":null},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2109.06939","title":"The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders","created":"2021-09-14","cited_by_count":32,"area":null},{"id":"2202.12891","title":"Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects","created":"2022-02-25","cited_by_count":32,"area":null},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2107.08765","title":"Adaptive Transfer Learning on Graph Neural Networks","created":"2021-07-19","cited_by_count":31,"area":null},{"id":"2305.10263","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","created":"2023-05-17","cited_by_count":30,"area":null},{"id":"2205.00305","title":"AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks","created":"2022-04-30","cited_by_count":29,"area":null},{"id":"2104.02443","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"area":null},{"id":"2203.06728","title":"SciNLI: A Corpus for Natural Language Inference on Scientific Text","created":"2022-03-13","cited_by_count":27,"area":null},{"id":"2308.12029","title":"Dual-Balancing for Multi-Task Learning","created":"2023-08-23","cited_by_count":27,"area":null},{"id":"2205.06126","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","created":"2022-05-12","cited_by_count":26,"area":null},{"id":"2401.13986","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","created":"2024-01-25","cited_by_count":26,"area":null},{"id":"2108.08983","title":"SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23,"area":null},{"id":"2105.14095","title":"Weighted Training for Cross-Task Learning","created":"2021-05-28","cited_by_count":22,"area":null},{"id":"2109.04912","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","created":"2021-09-10","cited_by_count":22,"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":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","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":"2204.06644","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2304.07854","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","created":"2023-04-16","cited_by_count":20,"area":null},{"id":"2103.11800","title":"AngryBERT: Joint Learning Target and Emotion for Hate Speech Detection","created":"2021-03-14","cited_by_count":19,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2205.11194","title":"UnifieR: A Unified Retriever for Large-Scale Retrieval","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2304.08109","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2305.03130","title":"Chain-of-Skills: A Configurable Model for Open-domain Question Answering","created":"2023-05-04","cited_by_count":19,"area":null},{"id":"2110.02370","title":"Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning","created":"2021-10-05","cited_by_count":18,"area":null},{"id":"2205.13267","title":"Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing","created":"2022-05-26","cited_by_count":18,"area":null},{"id":"2210.08471","title":"Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion","created":"2022-10-16","cited_by_count":18,"area":null},{"id":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2102.00272","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","created":"2021-01-30","cited_by_count":17,"area":null},{"id":"2111.01338","title":"Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training","created":"2021-11-02","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":"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":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17,"area":null},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16,"area":null},{"id":"2205.04605","title":"Sentence-level Privacy for Document Embeddings","created":"2022-05-10","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":"2208.05379","title":"Multi-task Active Learning for Pre-trained Transformer-based Models","created":"2022-08-10","cited_by_count":16,"area":null},{"id":"2305.14232","title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2105.11696","title":"Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation","created":"2021-05-25","cited_by_count":15,"area":null},{"id":"2110.08413","title":"Invariant Language Modeling","created":"2021-10-16","cited_by_count":15,"area":null},{"id":"2112.01047","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","created":"2021-12-02","cited_by_count":15,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"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":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2203.08565","title":"Geographic Adaptation of Pretrained Language Models","created":"2022-03-16","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":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14,"area":null}],"next_cursor":"100"}