{"total":82,"rows":[{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512,"area":null},{"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":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938,"area":null},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149,"area":null},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148,"area":null},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147,"area":"lr"},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127,"area":null},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123,"area":null},{"id":"2303.01229","title":"Almanac: Retrieval-Augmented Language Models for Clinical Medicine","created":"2023-03-01","cited_by_count":123,"area":"rag"},{"id":"2401.06432","title":"Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models","created":"2024-01-12","cited_by_count":116,"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":"2209.15240","title":"Universal Prompt Tuning for Graph Neural Networks","created":"2022-09-30","cited_by_count":100,"area":null},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2206.06122","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","created":"2022-06-13","cited_by_count":50,"area":null},{"id":"2305.13299","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","created":"2023-05-22","cited_by_count":49,"area":null},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2304.09960","title":"A Latent Space Theory for Emergent Abilities in Large Language Models","created":"2023-04-19","cited_by_count":43,"area":null},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2504.10957","title":"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers","created":"2025-04-15","cited_by_count":38,"area":"safety"},{"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":"2305.18787","title":"Universality and Limitations of Prompt Tuning","created":"2023-05-30","cited_by_count":30,"area":null},{"id":"2209.15210","title":"Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation","created":"2022-09-30","cited_by_count":25,"area":null},{"id":"2311.00233","title":"Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions","created":"2023-11-01","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":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2409.13853","title":"Unlocking Memorization in Large Language Models with Dynamic Soft Prompting","created":"2024-09-20","cited_by_count":21,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2303.07223","title":"PromptFusion: Decoupling Stability and Plasticity for Continual Learning","created":"2023-03-13","cited_by_count":17,"area":null},{"id":"2210.02952","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","created":"2022-10-06","cited_by_count":15,"area":null},{"id":"2406.04619","title":"CTSyn: A Foundation Model for Cross Tabular Data Generation","created":"2024-06-07","cited_by_count":14,"area":"diffusion"},{"id":"2303.02909","title":"Dynamic Prompting: A Unified Framework for Prompt Tuning","created":"2023-03-06","cited_by_count":12,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2201.05613","title":"The Dark Side of the Language: Pre-trained Transformers in the DarkNet","created":"2022-01-14","cited_by_count":10,"area":null},{"id":"2211.13638","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2110.08462","title":"Leveraging Knowledge in Multilingual Commonsense Reasoning","created":"2021-10-16","cited_by_count":9,"area":null},{"id":"2309.10448","title":"Human-AI Interactions and Societal Pitfalls","created":"2023-09-19","cited_by_count":9,"area":null},{"id":"2410.09605","title":"Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8,"area":"wm"},{"id":"2507.11588","title":"SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics","created":"2025-07-15","cited_by_count":8,"area":null},{"id":"2510.16670","title":"All You Need is One: Capsule Prompt Tuning with a Single Vector","created":"2025-10-19","cited_by_count":8,"area":null},{"id":"2403.11311","title":"Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding","created":"2024-03-17","cited_by_count":7,"area":null},{"id":"2501.16971","title":"RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2509.03036","title":"Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models","created":"2025-09-03","cited_by_count":7,"area":null},{"id":"2502.16849","title":"Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2503.03920","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2202.09305","title":"Masked prediction tasks: a parameter identifiability view","created":"2022-02-18","cited_by_count":4,"area":null},{"id":"2411.12600","title":"Provable unlearning in topic modeling and downstream tasks","created":"2024-11-19","cited_by_count":4,"area":"safety"},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2203.03539","title":"Understanding The Robustness of Self-supervised Learning Through Topic Modeling","created":"2022-02-02","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":"2309.02011","title":"Representation Learning Dynamics of Self-Supervised Models","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2409.15815","title":"AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support","created":"2024-09-24","cited_by_count":3,"area":"rag"},{"id":"2505.07637","title":"Chronocept: Instilling a Sense of Time in Machines","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2508.17233","title":"Module-Aware Parameter-Efficient Machine Unlearning on Transformers","created":"2025-08-24","cited_by_count":3,"area":"safety"},{"id":"2212.03760","title":"Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2510.26302","title":"Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2110.15712","title":"Analysing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2301.09820","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2310.02405","title":"PCGPT: Procedural Content Generation via Transformers","created":"2023-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2310.16261","title":"The Distributional Hypothesis Does Not Fully Explain the Benefits of Masked Language Model Pretraining","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2311.08687","title":"An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2401.01667","title":"MLPs Compass: What is learned when MLPs are combined with PLMs?","created":"2024-01-03","cited_by_count":1,"area":null},{"id":"2402.06884","title":"Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2403.08673","title":"When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2604.06440","title":"Visual prompting reimagined: The power of the Activation Prompts","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2302.12715","title":"Hiding Data Helps: On the Benefits of Masking for Sparse Coding","created":"2023-02-24","cited_by_count":0,"area":null},{"id":"2401.14166","title":"BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction","created":"2024-01-25","cited_by_count":0,"area":null},{"id":"2406.14142","title":"Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2410.00699","title":"Investigating the Impact of Model Complexity in Large Language Models","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2501.13031","title":"A Probabilistic Model for Non-Contrastive Learning","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2505.12304","title":"Pre-trained Prompt-driven Semi-supervised Local Community Detection","created":"2025-05-18","cited_by_count":0,"area":null},{"id":"2505.17135","title":"When can isotropy help adapt LLMs' next word prediction to numerical domains?","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2602.00969","title":"On the Spectral Flattening of Quantized Embeddings","created":"2026-02-01","cited_by_count":0,"area":null}],"next_cursor":null}