{"total":35,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73,"area":null},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41,"area":null},{"id":"2305.14327","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","created":"2023-05-23","cited_by_count":38,"area":null},{"id":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27,"area":null},{"id":"2502.19103","title":"LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm","created":"2025-02-26","cited_by_count":14,"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":"2409.12958","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","created":"2024-09-19","cited_by_count":12,"area":null},{"id":"2410.24175","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","created":"2024-10-31","cited_by_count":11,"area":null},{"id":"2404.02127","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","created":"2024-04-02","cited_by_count":10,"area":null},{"id":"2410.23463","title":"MDCure: A Scalable Pipeline for Multi-Document Instruction-Following","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2505.20658","title":"Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2501.09368","title":"Aligning Instruction Tuning with Pre-training","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2308.12711","title":"Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models","created":"2023-08-24","cited_by_count":6,"area":null},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2408.17437","title":"SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists","created":"2024-08-30","cited_by_count":6,"area":null},{"id":"2410.13464","title":"IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2407.10994","title":"Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2408.10663","title":"REInstruct: Building Instruction Data from Unlabeled Corpus","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2506.01484","title":"LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.16024","title":"From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2504.18804","title":"Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation","created":"2025-04-26","cited_by_count":3,"area":null},{"id":"2409.18943","title":"Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2503.22973","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.16922","title":"A Unifying Scheme for Extractive Content Selection Tasks","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2507.23440","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2510.07074","title":"LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2604.19071","title":"HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2607.06145","title":"Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2306.02334","title":"Long Text Generation Challenge","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2309.11000","title":"Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2504.12913","title":"MAIN: Mutual Alignment Is Necessary for instruction tuning","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2606.07690","title":"HARP: Efficient Data Selection for Finetuning Large Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.09875","title":"Integrating Local and Global Entropy for Uncertainty Quantification in LLMs","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}