{"list":"other","total":56,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2403.03883","title":"SaulLM-7B: A pioneering Large Language Model for Law","created":"2024-03-06","cited_by_count":142},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130},{"id":"2308.07074","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","created":"2023-08-14","cited_by_count":109},{"id":"2311.15653","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","created":"2023-11-27","cited_by_count":107},{"id":"2402.13064","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","created":"2024-02-20","cited_by_count":99},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68},{"id":"2307.06290","title":"Instruction Mining: Instruction Data Selection for Tuning Large Language Models","created":"2023-07-12","cited_by_count":58},{"id":"2402.10110","title":"Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning","created":"2024-02-15","cited_by_count":57},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48},{"id":"2312.10302","title":"One-Shot Learning as Instruction Data Prospector for Large Language Models","created":"2023-12-16","cited_by_count":43},{"id":"2402.10379","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","created":"2024-02-16","cited_by_count":43},{"id":"2312.14187","title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","created":"2023-12-20","cited_by_count":42},{"id":"2403.01081","title":"LAB: Large-Scale Alignment for ChatBots","created":"2024-03-02","cited_by_count":39},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33},{"id":"2305.16635","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","created":"2023-05-26","cited_by_count":31},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27},{"id":"2406.00770","title":"Automatic Instruction Evolving for Large Language Models","created":"2024-06-02","cited_by_count":26},{"id":"2410.06215","title":"DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback","created":"2024-10-08","cited_by_count":25},{"id":"2501.12273","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","created":"2025-01-21","cited_by_count":18},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9},{"id":"2408.13467","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","created":"2024-08-24","cited_by_count":8},{"id":"2310.13008","title":"DavIR: Data Selection via Implicit Reward for Large Language Models","created":"2023-10-16","cited_by_count":6},{"id":"2412.17365","title":"Boosting LLM via Learning from Data Iteratively and Selectively","created":"2024-12-23","cited_by_count":1}],"next_cursor":null}