{"total":139,"rows":[{"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":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952,"area":"rag"},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326,"area":null},{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296,"area":null},{"id":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232,"area":null},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204,"area":null},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199,"area":null},{"id":"2109.07830","title":"Reframing Instructional Prompts to GPTk's Language","created":"2021-09-16","cited_by_count":176,"area":null},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"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":"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":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2304.06648","title":"DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning","created":"2023-04-13","cited_by_count":84,"area":"diffusion"},{"id":"2203.08410","title":"Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again","created":"2022-03-16","cited_by_count":83,"area":"lr"},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2311.16119","title":"Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition","created":"2023-10-24","cited_by_count":68,"area":"safety"},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2204.05239","title":"Exploring the Universal Vulnerability of Prompt-based Learning Paradigm","created":"2022-04-11","cited_by_count":57,"area":null},{"id":"2205.07830","title":"FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization","created":"2022-05-16","cited_by_count":49,"area":null},{"id":"2402.10294","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","created":"2024-02-15","cited_by_count":47,"area":"agents"},{"id":"2205.10475","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","created":"2022-05-21","cited_by_count":45,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2311.01967","title":"The language of prompting: What linguistic properties make a prompt successful?","created":"2023-11-03","cited_by_count":44,"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":"2210.03304","title":"Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding","created":"2022-10-07","cited_by_count":40,"area":null},{"id":"2211.00295","title":"CONDAQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation","created":"2022-11-01","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":"2211.03044","title":"Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning","created":"2022-11-06","cited_by_count":36,"area":null},{"id":"2308.11224","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","created":"2023-08-22","cited_by_count":35,"area":null},{"id":"2402.15734","title":"Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning","created":"2024-02-24","cited_by_count":32,"area":null},{"id":"2109.06050","title":"Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training","created":"2021-09-13","cited_by_count":28,"area":null},{"id":"2308.13894","title":"FwdLLM: Efficient FedLLM using Forward Gradient","created":"2023-08-26","cited_by_count":26,"area":null},{"id":"2304.05263","title":"Prompt Learning for News Recommendation","created":"2023-04-11","cited_by_count":25,"area":null},{"id":"2212.02216","title":"Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration","created":"2022-12-05","cited_by_count":24,"area":null},{"id":"2305.12766","title":"Understanding Emergent In-Context Learning from a Kernel Regression Perspective","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2212.06950","title":"Pre-trained Language Models Can be Fully Zero-Shot Learners","created":"2022-12-14","cited_by_count":22,"area":null},{"id":"2112.07868","title":"Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases","created":"2021-12-15","cited_by_count":21,"area":null},{"id":"2109.06513","title":"Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation","created":"2021-09-14","cited_by_count":20,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"area":null},{"id":"2310.14034","title":"Tree Prompting: Efficient Task Adaptation without Fine-Tuning","created":"2023-10-21","cited_by_count":18,"area":null},{"id":"2402.12819","title":"Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance","created":"2024-02-20","cited_by_count":18,"area":null},{"id":"2405.15614","title":"Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study","created":"2024-05-24","cited_by_count":17,"area":null},{"id":"2310.14201","title":"Prompt Engineering Through the Lens of Optimal Control","created":"2023-10-22","cited_by_count":16,"area":null},{"id":"2203.14655","title":"Few-Shot Learning with Siamese Networks and Label Tuning","created":"2022-03-28","cited_by_count":15,"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":"2211.09783","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2212.05974","title":"Federated Few-Shot Learning for Mobile NLP","created":"2022-12-12","cited_by_count":15,"area":null},{"id":"2204.04413","title":"PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization","created":"2022-04-09","cited_by_count":14,"area":null},{"id":"2304.05051","title":"FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training","created":"2023-04-11","cited_by_count":14,"area":"mllm"},{"id":"2305.14926","title":"Universal Self-Adaptive Prompting","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2201.08670","title":"Context-Tuning: Learning Contextualized Prompts for Natural Language Generation","created":"2022-01-21","cited_by_count":12,"area":null},{"id":"2210.10841","title":"Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language Models","created":"2022-10-19","cited_by_count":12,"area":"mllm"},{"id":"2305.07406","title":"Two-in-One: A Model Hijacking Attack Against Text Generation Models","created":"2023-05-12","cited_by_count":12,"area":null},{"id":"2501.10860","title":"Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking","created":"2025-01-18","cited_by_count":12,"area":null},{"id":"2210.10693","title":"Robustness of Demonstration-based Learning Under Limited Data Scenario","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2211.08099","title":"A Universal Discriminator for Zero-Shot Generalization","created":"2022-11-15","cited_by_count":11,"area":null},{"id":"2305.01598","title":"From Words to Code: Harnessing Data for Program Synthesis from Natural Language","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2405.17825","title":"Diffusion Model Patching via Mixture-of-Prompts","created":"2024-05-28","cited_by_count":11,"area":"diffusion"},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2411.17722","title":"When IoT Meet LLMs: Applications and Challenges","created":"2024-11-20","cited_by_count":11,"area":null},{"id":"2210.10258","title":"Continued Pretraining for Better Zero- and Few-Shot Promptability","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2304.07840","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","created":"2023-04-16","cited_by_count":10,"area":null},{"id":"2405.20770","title":"Large Language Model Sentinel: LLM Agent for Adversarial Purification","created":"2024-05-24","cited_by_count":10,"area":"agents"},{"id":"2412.00765","title":"SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts","created":"2024-12-01","cited_by_count":10,"area":"safety"},{"id":"2111.02570","title":"CLUES: Few-Shot Learning Evaluation in Natural Language Understanding","created":"2021-11-04","cited_by_count":9,"area":null},{"id":"2210.02771","title":"Modelling Commonsense Properties using Pre-Trained Bi-Encoders","created":"2022-10-06","cited_by_count":9,"area":null},{"id":"2305.17442","title":"Weaker Than You Think: A Critical Look at Weakly Supervised Learning","created":"2023-05-27","cited_by_count":8,"area":null},{"id":"2402.10353","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2509.14404","title":"A Taxonomy of Prompt Defects in LLM Systems","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2210.13838","title":"Multilingual Relation Classification via Efficient and Effective Prompting","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2309.09276","title":"MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification","created":"2023-09-17","cited_by_count":7,"area":null},{"id":"2407.19568","title":"Are LLMs Good Annotators for Discourse-level Event Relation Extraction?","created":"2024-07-28","cited_by_count":7,"area":null},{"id":"2408.00686","title":"Can Developers Prompt? A Controlled Experiment for Code Documentation Generation","created":"2024-08-01","cited_by_count":7,"area":null},{"id":"2504.03159","title":"Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction","created":"2025-04-04","cited_by_count":7,"area":null},{"id":"2212.06645","title":"Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2312.14646","title":"Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference","created":"2023-12-22","cited_by_count":6,"area":null},{"id":"2203.00902","title":"Do Prompts Solve NLP Tasks Using Natural Language?","created":"2022-03-02","cited_by_count":5,"area":null},{"id":"2303.03840","title":"A Challenging Benchmark for Low-Resource Learning","created":"2023-03-07","cited_by_count":5,"area":null},{"id":"2306.04101","title":"Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2406.07935","title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2205.12643","title":"Asking the Right Questions in Low Resource Template Extraction","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2210.04695","title":"Language Models Are Poor Learners of Directional Inference","created":"2022-10-10","cited_by_count":4,"area":null},{"id":"2211.09113","title":"On Measuring the Intrinsic Few-Shot Hardness of Datasets","created":"2022-11-16","cited_by_count":4,"area":null},{"id":"2310.06174","title":"Cost-Efficient Prompt Engineering for Unsupervised Entity Resolution","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2310.13998","title":"Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models","created":"2023-10-21","cited_by_count":4,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2406.06736","title":"Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges","created":"2024-06-10","cited_by_count":4,"area":null},{"id":"2406.10878","title":"Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2409.15441","title":"Steward: Natural Language Web Automation","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2202.07255","title":"Enhancing Cross-lingual Prompting with Dual Prompt Augmentation","created":"2022-02-15","cited_by_count":3,"area":null},{"id":"2307.00097","title":"Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation","created":"2023-06-30","cited_by_count":3,"area":null},{"id":"2310.18358","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","created":"2023-10-24","cited_by_count":3,"area":null}],"next_cursor":"100"}