{"total":128,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868,"area":null},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686,"area":null},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"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":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2212.09741","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","created":"2022-12-19","cited_by_count":333,"area":null},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269,"area":null},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263,"area":null},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248,"area":"agents"},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"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":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"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":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193,"area":null},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164,"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":"2209.15189","title":"Learning by Distilling Context","created":"2022-09-30","cited_by_count":138,"area":null},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110,"area":"lr"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2304.14293","title":"Controlled Text Generation with Natural Language Instructions","created":"2023-04-27","cited_by_count":87,"area":null},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86,"area":null},{"id":"2310.19596","title":"LLMaAA: Making Large Language Models as Active Annotators","created":"2023-10-30","cited_by_count":79,"area":null},{"id":"2309.15649","title":"Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting","created":"2023-09-27","cited_by_count":72,"area":null},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70,"area":null},{"id":"2406.08660","title":"Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification","created":"2024-06-12","cited_by_count":70,"area":null},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","cited_by_count":67,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","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":"2201.06910","title":"ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization","created":"2022-01-18","cited_by_count":54,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2305.13455","title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","created":"2023-05-22","cited_by_count":54,"area":"agents"},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2305.12147","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","created":"2023-05-20","cited_by_count":31,"area":"lr"},{"id":"2310.13486","title":"Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning","created":"2023-10-20","cited_by_count":31,"area":null},{"id":"2212.10711","title":"Task Ambiguity in Humans and Language Models","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2304.13188","title":"TABLET: Learning From Instructions For Tabular Data","created":"2023-04-25","cited_by_count":28,"area":null},{"id":"2205.13792","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","created":"2022-05-27","cited_by_count":27,"area":"rag"},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"area":"synth"},{"id":"2305.10703","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2309.01664","title":"Fine-grained Affective Processing Capabilities Emerging from Large Language Models","created":"2023-09-04","cited_by_count":24,"area":null},{"id":"2302.08624","title":"InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis","created":"2023-02-16","cited_by_count":23,"area":null},{"id":"2407.08440","title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","created":"2024-07-11","cited_by_count":23,"area":null},{"id":"2304.07854","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","created":"2023-04-16","cited_by_count":20,"area":null},{"id":"2209.11486","title":"MetaPrompting: Learning to Learn Better Prompts","created":"2022-09-23","cited_by_count":19,"area":null},{"id":"2304.08109","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2205.05313","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2301.08771","title":"Matching Exemplar as Next Sentence Prediction (MeNSP): Zero-shot Prompt Learning for Automatic Scoring in Science Education","created":"2023-01-20","cited_by_count":18,"area":null},{"id":"2206.02873","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","created":"2022-06-06","cited_by_count":17,"area":null},{"id":"2208.08232","title":"HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models","created":"2022-08-17","cited_by_count":17,"area":"lr"},{"id":"2406.13846","title":"Text Serialization and Their Relationship with the Conventional Paradigms of Tabular Machine Learning","created":"2024-06-19","cited_by_count":17,"area":null},{"id":"2502.04688","title":"M-IFEval: Multilingual Instruction-Following Evaluation","created":"2025-02-07","cited_by_count":17,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"area":null},{"id":"2203.08378","title":"Transforming Sequence Tagging Into A Seq2Seq Task","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2310.14495","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2109.08079","title":"Context-NER : Contextual Phrase Generation at Scale","created":"2021-09-16","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2305.15689","title":"Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2305.09025","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2204.09148","title":"What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment","created":"2022-04-19","cited_by_count":9,"area":null},{"id":"2411.04709","title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2506.08375","title":"EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2112.07660","title":"Massive-scale Decoding for Text Generation using Lattices","created":"2021-12-14","cited_by_count":8,"area":null},{"id":"2205.15172","title":"Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task","created":"2022-05-30","cited_by_count":8,"area":null},{"id":"2111.00865","title":"MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition","created":"2021-10-27","cited_by_count":7,"area":null},{"id":"2203.13602","title":"ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations","created":"2022-03-25","cited_by_count":7,"area":null},{"id":"2212.10708","title":"Zero-shot Triplet Extraction by Template Infilling","created":"2022-12-21","cited_by_count":7,"area":null},{"id":"2310.08796","title":"End-to-end Story Plot Generator","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2404.02261","title":"LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2305.11442","title":"Zero-Shot Text Classification via Self-Supervised Tuning","created":"2023-05-19","cited_by_count":6,"area":null},{"id":"2312.04945","title":"The ICL Consistency Test","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2303.01593","title":"QAID: Question Answering Inspired Few-shot Intent Detection","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2506.00815","title":"Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2304.09402","title":"MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2305.14592","title":"Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding","created":"2023-05-24","cited_by_count":4,"area":null}],"next_cursor":"100"}