{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"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":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"1807.00734","title":"The relativistic discriminator: a key element missing from standard GAN","created":"2018-07-02","cited_by_count":238},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2312.16682","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","created":"2023-12-27","cited_by_count":108},{"id":"2303.04132","title":"Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction","created":"2023-03-07","cited_by_count":89},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70},{"id":"1811.00739","title":"An Empirical Exploration of Curriculum Learning for Neural Machine Translation","created":"2018-11-02","cited_by_count":58},{"id":"1909.12823","title":"A Generalized Training Approach for Multiagent Learning","created":"2019-09-27","cited_by_count":54},{"id":"1611.06204","title":"Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks","created":"2016-11-18","cited_by_count":44},{"id":"2311.08045","title":"Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game","created":"2023-11-14","cited_by_count":27},{"id":"1705.09675","title":"Fisher GAN","created":"2017-05-26","cited_by_count":22},{"id":"2106.13805","title":"Self-training Converts Weak Learners to Strong Learners in Mixture Models","created":"2021-06-25","cited_by_count":19},{"id":"2310.05861","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models","created":"2023-10-09","cited_by_count":14},{"id":"2312.02418","title":"Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data","created":"2023-12-05","cited_by_count":12},{"id":"2211.02077","title":"Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization","created":"2022-11-03","cited_by_count":9}],"next_cursor":null}