{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"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":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"1903.09848","title":"Competence-based Curriculum Learning for Neural Machine Translation","created":"2019-03-23","cited_by_count":202},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2307.14430","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","created":"2023-07-26","cited_by_count":121},{"id":"2311.15653","title":"MoDS: Model-oriented Data Selection for Instruction Tuning","created":"2023-11-27","cited_by_count":107},{"id":"1410.4615","title":"Learning to Execute","created":"2014-10-17","cited_by_count":106},{"id":"2012.03107","title":"When Do Curricula Work?","created":"2020-12-05","cited_by_count":106},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105},{"id":"2406.06046","title":"MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models","created":"2024-06-10","cited_by_count":100},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84},{"id":"1905.10847","title":"Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives","created":"2019-05-26","cited_by_count":59},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57},{"id":"1705.08280","title":"How hard can it be? Estimating the difficulty of visual search in an image","created":"2017-05-23","cited_by_count":52},{"id":"2311.08182","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","created":"2023-11-14","cited_by_count":52},{"id":"2405.13637","title":"Curriculum Direct Preference Optimization for Diffusion and Consistency Models","created":"2024-05-22","cited_by_count":36},{"id":"2102.03554","title":"Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning","created":"2021-02-06","cited_by_count":34},{"id":"2312.11508","title":"Rethinking the Instruction Quality: LIFT is What You Need","created":"2023-12-12","cited_by_count":34},{"id":"2108.02170","title":"Curriculum learning for language modeling","created":"2021-08-04","cited_by_count":32},{"id":"2406.14785","title":"Understanding Finetuning for Factual Knowledge Extraction","created":"2024-06-20","cited_by_count":32},{"id":"2405.07490","title":"Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning","created":"2024-05-13","cited_by_count":28},{"id":"2402.07610","title":"Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping","created":"2024-02-12","cited_by_count":14},{"id":"2308.01472","title":"Reverse Stable Diffusion: What prompt was used to generate this image?","created":"2023-08-02","cited_by_count":7},{"id":"2407.00102","title":"Curriculum Learning with Quality-Driven Data Selection","created":"2024-06-27","cited_by_count":7},{"id":"2205.07427","title":"Exploring the Learning Difficulty of Data Theory and Measure","created":"2022-05-16","cited_by_count":4},{"id":"2411.00973","title":"Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning","created":"2024-11-01","cited_by_count":3},{"id":"2402.19267","title":"Robust Guidance for Unsupervised Data Selection: Capturing Perplexing Named Entities for Domain-Specific Machine Translation","created":"2024-02-29","cited_by_count":1}],"next_cursor":null}