{"total":384,"rows":[{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694,"area":null},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567,"area":null},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255,"area":null},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238,"area":null},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236,"area":null},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198,"area":null},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183,"area":"mllm"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156,"area":null},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147,"area":null},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"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":"2106.13353","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","created":"2021-06-24","cited_by_count":139,"area":null},{"id":"2209.11055","title":"Efficient Few-Shot Learning Without Prompts","created":"2022-09-22","cited_by_count":137,"area":null},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2208.11625","title":"PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Model","created":"2022-08-24","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":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110,"area":null},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"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":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83,"area":null},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81,"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":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76,"area":null},{"id":"2305.02317","title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","created":"2023-05-03","cited_by_count":69,"area":"lr"},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2401.08508","title":"EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis","created":"2024-01-16","cited_by_count":62,"area":null},{"id":"2208.00406","title":"Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI","created":"2022-07-31","cited_by_count":58,"area":null},{"id":"2511.08567","title":"The Path Not Taken: RLVR Provably Learns Off the Principals","created":"2025-11-11","cited_by_count":56,"area":"lr"},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2401.04350","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","created":"2024-01-09","cited_by_count":48,"area":"mllm"},{"id":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44,"area":null},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44,"area":null},{"id":"2311.13534","title":"LM-Cocktail: Resilient Tuning of Language Models via Model Merging","created":"2023-11-22","cited_by_count":44,"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":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41,"area":null},{"id":"2312.17493","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","created":"2023-12-29","cited_by_count":41,"area":null},{"id":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38,"area":null},{"id":"2203.12175","title":"Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing","created":"2022-03-23","cited_by_count":38,"area":null},{"id":"2405.13055","title":"Large Language Models for Medicine: A Survey","created":"2024-05-20","cited_by_count":38,"area":null},{"id":"2202.08036","title":"No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices","created":"2022-02-16","cited_by_count":37,"area":null},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2310.09832","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","created":"2023-10-15","cited_by_count":37,"area":"moe"},{"id":"2311.06102","title":"Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking","created":"2023-11-10","cited_by_count":37,"area":null},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36,"area":null},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"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":"2408.08345","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","created":"2024-08-15","cited_by_count":34,"area":null},{"id":"2204.04213","title":"Structure-aware Protein Self-supervised Learning","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2104.08320","title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"area":null},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30,"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":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2312.01454","title":"D-Bot: Database Diagnosis System using Large Language Models","created":"2023-12-03","cited_by_count":28,"area":null},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2308.01589","title":"Holy Grail 2.0: From Natural Language to Constraint Models","created":"2023-08-03","cited_by_count":26,"area":null},{"id":"2508.13144","title":"Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation","created":"2025-08-18","cited_by_count":26,"area":null},{"id":"2109.03537","title":"On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets","created":"2021-09-08","cited_by_count":25,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25,"area":null},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25,"area":"lr"},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2305.03731","title":"Working Memory Capacity of ChatGPT: An Empirical Study","created":"2023-04-30","cited_by_count":23,"area":null},{"id":"2305.13404","title":"Improving Convergence and Generalization Using Parameter Symmetries","created":"2023-05-22","cited_by_count":23,"area":null},{"id":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22,"area":"distill"},{"id":"2110.14171","title":"Diversity Enhanced Active Learning with Strictly Proper Scoring Rules","created":"2021-10-27","cited_by_count":22,"area":null},{"id":"2304.01910","title":"On the Variance of Neural Network Training with respect to Test Sets and Distributions","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2410.22815","title":"Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients","created":"2024-10-30","cited_by_count":22,"area":null},{"id":"2109.03160","title":"How much pretraining data do language models need to learn syntax?","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null}],"next_cursor":"100"}