{"total":198,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141,"area":"rag"},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897,"area":"wm"},{"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":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722,"area":null},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658,"area":null},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2106.03004","title":"Exploring the Limits of Out-of-Distribution Detection","created":"2021-06-06","cited_by_count":283,"area":null},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272,"area":null},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251,"area":null},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241,"area":"wm"},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162,"area":null},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124,"area":null},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123,"area":null},{"id":"2108.13888","title":"Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning","created":"2021-08-31","cited_by_count":113,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95,"area":null},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89,"area":null},{"id":"2103.06561","title":"WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training","created":"2021-03-11","cited_by_count":84,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2301.03150","title":"MOTOR: A Time-To-Event Foundation Model For Structured Medical Records","created":"2023-01-09","cited_by_count":78,"area":null},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2406.05207","title":"Retrieval & Fine-Tuning for In-Context Tabular Models","created":"2024-06-07","cited_by_count":59,"area":null},{"id":"2206.02338","title":"OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression","created":"2022-06-06","cited_by_count":44,"area":null},{"id":"2204.11073","title":"Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps","created":"2022-04-23","cited_by_count":42,"area":null},{"id":"2407.07890","title":"Training on the Test Task Confounds Evaluation and Emergence","created":"2024-07-10","cited_by_count":34,"area":null},{"id":"2307.10683","title":"Fractional Denoising for 3D Molecular Pre-training","created":"2023-07-20","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":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29,"area":null},{"id":"2110.06282","title":"The Rich Get Richer: Disparate Impact of Semi-Supervised Learning","created":"2021-10-12","cited_by_count":28,"area":null},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","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":"2310.15290","title":"Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Models","created":"2023-10-23","cited_by_count":24,"area":null},{"id":"2110.03618","title":"Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2205.11739","title":"Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21,"area":null},{"id":"2201.03110","title":"Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning","created":"2022-01-09","cited_by_count":19,"area":null},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2308.04399","title":"Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Models","created":"2023-08-08","cited_by_count":17,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2101.06351","title":"Weakly-Supervised Hierarchical Models for Predicting Persuasive Strategies in Good-faith Textual Requests","created":"2021-01-16","cited_by_count":16,"area":null},{"id":"2102.11903","title":"Neural ranking models for document retrieval","created":"2021-02-23","cited_by_count":16,"area":null},{"id":"2104.08942","title":"Attention-based Clinical Note Summarization","created":"2021-04-18","cited_by_count":16,"area":null},{"id":"2102.08924","title":"Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detection","created":"2021-02-17","cited_by_count":15,"area":null},{"id":"2203.11242","title":"A survey on GANs for computer vision: Recent research, analysis and taxonomy","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2205.11726","title":"On the Role of Bidirectionality in Language Model Pre-Training","created":"2022-05-24","cited_by_count":15,"area":null},{"id":"2102.01792","title":"A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2103.03629","title":"Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification","created":"2021-03-05","cited_by_count":14,"area":null},{"id":"2108.02598","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","created":"2021-08-05","cited_by_count":14,"area":"distill"},{"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":"2402.04841","title":"Data-efficient Large Vision Models through Sequential Autoregression","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2407.11086","title":"Pre-training with Fractional Denoising to Enhance Molecular Property Prediction","created":"2024-07-14","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2402.04286","title":"Progress and Opportunities of Foundation Models in Bioinformatics","created":"2024-02-06","cited_by_count":13,"area":null},{"id":"2411.02083","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2111.02622","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","created":"2021-11-04","cited_by_count":12,"area":null},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2207.11765","title":"Neurosymbolic Repair for Low-Code Formula Languages","created":"2022-07-24","cited_by_count":12,"area":null},{"id":"2205.10981","title":"Improving Short Text Classification With Augmented Data Using GPT-3","created":"2022-05-23","cited_by_count":11,"area":null},{"id":"2305.14596","title":"Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2503.01372","title":"SwiLTra-Bench: The Swiss Legal Translation Benchmark","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2102.03062","title":"Understanding Emails and Drafting Responses -- An Approach Using GPT-3","created":"2021-02-05","cited_by_count":10,"area":null},{"id":"2104.13913","title":"Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction","created":"2021-04-28","cited_by_count":10,"area":null},{"id":"2310.16538","title":"FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2509.24368","title":"Watermarking Diffusion Language Models","created":"2025-09-29","cited_by_count":10,"area":"diffusion"},{"id":"2107.08957","title":"Clinical Relation Extraction Using Transformer-based Models","created":"2021-07-19","cited_by_count":9,"area":null},{"id":"2109.10234","title":"BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets","created":"2021-09-21","cited_by_count":9,"area":null},{"id":"2209.03563","title":"SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning","created":"2022-09-08","cited_by_count":9,"area":null},{"id":"2211.05528","title":"PAD-Net: An Efficient Framework for Dynamic Networks","created":"2022-11-10","cited_by_count":9,"area":"moe"},{"id":"2308.12605","title":"APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency","created":"2023-08-24","cited_by_count":9,"area":"diffusion"},{"id":"2405.16820","title":"Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2104.00270","title":"Evaluating Neural Word Embeddings for Sanskrit","created":"2021-04-01","cited_by_count":8,"area":null},{"id":"2202.12935","title":"Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2206.01206","title":"Positive Unlabeled Contrastive Learning","created":"2022-06-01","cited_by_count":8,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2103.13799","title":"Bertinho: Galician BERT Representations","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2105.04642","title":"SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgery","created":"2021-05-10","cited_by_count":7,"area":null},{"id":"2306.02870","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2106.05478","title":"Semantic-aware Binary Code Representation with BERT","created":"2021-06-10","cited_by_count":6,"area":null},{"id":"2107.12168","title":"Exploiting Language Model for Efficient Linguistic Steganalysis","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2108.11950","title":"LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision","created":"2021-08-26","cited_by_count":6,"area":null}],"next_cursor":"100"}