{"total":126,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"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":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233,"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":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142,"area":null},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137,"area":null},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129,"area":null},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100,"area":null},{"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":"2301.07507","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2303.08518","title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation","created":"2023-03-15","cited_by_count":75,"area":null},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2307.07164","title":"Learning to Retrieve In-Context Examples for Large Language Models","created":"2023-07-14","cited_by_count":60,"area":null},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58,"area":null},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52,"area":null},{"id":"2402.02347","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2311.00636","title":"Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures","created":"2023-11-01","cited_by_count":49,"area":null},{"id":"2103.09120","title":"Structural Adapters in Pretrained Language Models for AMR-to-text Generation","created":"2021-03-16","cited_by_count":48,"area":null},{"id":"2109.02707","title":"Text-to-Table: A New Way of Information Extraction","created":"2021-09-06","cited_by_count":47,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43,"area":null},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2401.08295","title":"SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models","created":"2024-01-16","cited_by_count":38,"area":null},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2203.03131","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","created":"2022-03-07","cited_by_count":34,"area":null},{"id":"2110.08417","title":"Open Domain Question Answering with A Unified Knowledge Interface","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2205.03972","title":"Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning","created":"2022-05-08","cited_by_count":32,"area":null},{"id":"2403.09113","title":"AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning","created":"2024-03-14","cited_by_count":31,"area":null},{"id":"2206.14017","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","created":"2022-06-28","cited_by_count":30,"area":null},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29,"area":null},{"id":"2402.16671","title":"StructLM: Towards Building Generalist Models for Structured Knowledge Grounding","created":"2024-02-26","cited_by_count":29,"area":null},{"id":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2311.08002","title":"TempTabQA: Temporal Question Answering for Semi-Structured Tables","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2307.07312","title":"Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs","created":"2023-07-14","cited_by_count":24,"area":null},{"id":"2104.04243","title":"Incorporating External Knowledge to Enhance Tabular Reasoning","created":"2021-04-09","cited_by_count":23,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2402.01155","title":"CABINET: Content Relevance based Noise Reduction for Table Question Answering","created":"2024-02-02","cited_by_count":23,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2203.16279","title":"Neural Pipeline for Zero-Shot Data-to-Text Generation","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2211.08682","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","created":"2022-11-16","cited_by_count":19,"area":null},{"id":"2201.07126","title":"Instance-aware Prompt Learning for Language Understanding and Generation","created":"2022-01-18","cited_by_count":18,"area":null},{"id":"2212.04408","title":"OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2206.12131","title":"MVP: Multi-task Supervised Pre-training for Natural Language Generation","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2402.11218","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","created":"2024-02-17","cited_by_count":16,"area":null},{"id":"2104.08296","title":"Learning to Reason for Text Generation from Scientific Tables","created":"2021-04-16","cited_by_count":14,"area":null},{"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":"2210.04325","title":"ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models","created":"2022-10-09","cited_by_count":14,"area":null},{"id":"2306.16931","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2401.01183","title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","created":"2024-01-02","cited_by_count":13,"area":null},{"id":"2305.14987","title":"Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2401.10040","title":"Large Language Models for Scientific Information Extraction: An Empirical Study for Virology","created":"2024-01-18","cited_by_count":12,"area":null},{"id":"2105.08021","title":"Stage-wise Fine-tuning for Graph-to-Text Generation","created":"2021-05-17","cited_by_count":11,"area":null},{"id":"2107.13935","title":"Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition","created":"2021-07-29","cited_by_count":11,"area":null},{"id":"2302.11521","title":"How Does In-Context Learning Help Prompt Tuning?","created":"2023-02-22","cited_by_count":11,"area":null},{"id":"2410.03883","title":"DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2211.00142","title":"TaTa: A Multilingual Table-to-Text Dataset for African Languages","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2111.00160","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","created":"2021-10-30","cited_by_count":8,"area":null},{"id":"2205.11505","title":"What Makes Data-to-Text Generation Hard for Pretrained Language Models?","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2210.10599","title":"Self-supervised Graph Masking Pre-training for Graph-to-Text Generation","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2406.10976","title":"Promoting Data and Model Privacy in Federated Learning through Quantized LoRA","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2205.12410","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2302.14169","title":"TabGenie: A Toolkit for Table-to-Text Generation","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2305.14793","title":"Faithful Low-Resource Data-to-Text Generation through Cycle Training","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2210.07373","title":"Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2403.04124","title":"Privacy-preserving Fine-tuning of Large Language Models through Flatness","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2110.05633","title":"TCube: Domain-Agnostic Neural Time-series Narration","created":"2021-10-11","cited_by_count":5,"area":null},{"id":"2410.20163","title":"UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers","created":"2024-10-26","cited_by_count":5,"area":null},{"id":"2505.19966","title":"Learning to Select In-Context Demonstration Preferred by Large Language Model","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2112.05717","title":"Discourse-Aware Soft Prompting for Text Generation","created":"2021-12-10","cited_by_count":4,"area":null},{"id":"2210.12795","title":"Realistic Data Augmentation Framework for Enhancing Tabular Reasoning","created":"2022-10-23","cited_by_count":4,"area":null},{"id":"2307.14440","title":"Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2402.08496","title":"A Systematic Review of Data-to-Text NLG","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2212.01956","title":"Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2307.03313","title":"InfoSync: Information Synchronization across Multilingual Semi-structured Tables","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2308.08881","title":"Text-Only Training for Visual Storytelling","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2309.11065","title":"UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2401.15555","title":"Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion","created":"2024-01-28","cited_by_count":3,"area":null},{"id":"2403.07567","title":"Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation","created":"2024-03-12","cited_by_count":3,"area":null},{"id":"2409.07088","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2410.17859","title":"DataTales: A Benchmark for Real-World Intelligent Data Narration","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2511.07129","title":"LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2305.12394","title":"Pruning Pre-trained Language Models with Principled Importance and Self-regularization","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2308.05317","title":"Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning","created":"2023-08-10","cited_by_count":2,"area":null}],"next_cursor":"100"}