{"total":127,"rows":[{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375,"area":null},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"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":"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":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2102.11005","title":"LogME: Practical Assessment of Pre-trained Models for Transfer Learning","created":"2021-02-22","cited_by_count":172,"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":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134,"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":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"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":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","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":"2211.12485","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","created":"2022-11-22","cited_by_count":46,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2203.00633","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","created":"2022-03-01","cited_by_count":41,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2105.06020","title":"Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level","created":"2021-05-13","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":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2208.10160","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","created":"2022-08-22","cited_by_count":31,"area":"distill"},{"id":"2208.08408","title":"Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models","created":"2022-08-17","cited_by_count":30,"area":null},{"id":"2506.09022","title":"Do Multiple Instance Learning Models Transfer?","created":"2025-06-10","cited_by_count":29,"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":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","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":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2202.11451","title":"Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt","created":"2022-02-23","cited_by_count":25,"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":"2104.04243","title":"Incorporating External Knowledge to Enhance Tabular Reasoning","created":"2021-04-09","cited_by_count":23,"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":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2401.05906","title":"PartSTAD: 2D-to-3D Part Segmentation Task Adaptation","created":"2024-01-11","cited_by_count":18,"area":null},{"id":"2201.05222","title":"Assemble Foundation Models for Automatic Code Summarization","created":"2022-01-13","cited_by_count":17,"area":null},{"id":"2210.16771","title":"Parameter-Efficient Tuning Makes a Good Classification Head","created":"2022-10-30","cited_by_count":15,"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":"2302.00674","title":"Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data","created":"2023-02-01","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":"2205.15051","title":"X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents","created":"2022-05-30","cited_by_count":12,"area":null},{"id":"2102.06008","title":"Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Papers","created":"2021-02-11","cited_by_count":11,"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":"2109.13620","title":"Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking","created":"2021-09-28","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":"2104.02704","title":"Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2106.02278","title":"AgreeSum: Agreement-Oriented Multi-Document Summarization","created":"2021-06-04","cited_by_count":10,"area":null},{"id":"2203.07519","title":"Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer","created":"2022-03-14","cited_by_count":10,"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":"2210.13029","title":"Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models","created":"2022-10-24","cited_by_count":10,"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":"2110.08547","title":"Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation","created":"2021-10-16","cited_by_count":8,"area":null},{"id":"2306.07285","title":"TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills","created":"2023-05-23","cited_by_count":8,"area":"mechinterp"},{"id":"2404.08066","title":"MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference","created":"2024-04-11","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":"2104.07244","title":"TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction","created":"2021-04-15","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":"2205.03766","title":"Scheduled Multi-task Learning for Neural Chat Translation","created":"2022-05-08","cited_by_count":7,"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":"2304.02168","title":"I2I: Initializing Adapters with Improvised Knowledge","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2109.06605","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","created":"2021-09-14","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":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","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":"2504.21190","title":"TT-LoRA MoE: Unifying Parameter-Efficient Fine-Tuning and Sparse Mixture-of-Experts","created":"2025-04-29","cited_by_count":6,"area":"moe"},{"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":"2302.01530","title":"Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective","created":"2023-02-03","cited_by_count":5,"area":"distill"},{"id":"2407.01091","title":"M2QA: Multi-domain Multilingual Question Answering","created":"2024-07-01","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":"2109.07067","title":"Improving Text Auto-Completion with Next Phrase Prediction","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2204.02000","title":"The COVMis-Stance dataset: Stance Detection on Twitter for COVID-19 Misinformation","created":"2022-04-05","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":"2401.04025","title":"IDoFew: Intermediate Training Using Dual-Clustering in Language Models for Few Labels Text Classification","created":"2024-01-08","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":"2105.14879","title":"SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning","created":"2021-05-31","cited_by_count":3,"area":null},{"id":"2204.14114","title":"Developmental Negation Processing in Transformer Language Models","created":"2022-04-29","cited_by_count":3,"area":null},{"id":"2210.12259","title":"Enhancing Tabular Reasoning with Pattern Exploiting Training","created":"2022-10-21","cited_by_count":3,"area":"lr"},{"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":"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":"2203.16027","title":"Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2210.02989","title":"SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","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":"2211.00910","title":"PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation","created":"2022-11-02","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":"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}],"next_cursor":"100"}