{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"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":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"2312.01552","title":"The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning","created":"2023-12-04","cited_by_count":257},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156},{"id":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55},{"id":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45},{"id":"2402.18243","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","created":"2024-02-28","cited_by_count":43},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41},{"id":"2402.07625","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","created":"2024-02-12","cited_by_count":27},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23},{"id":"2403.07794","title":"Fine-tuning Large Language Models with Sequential Instructions","created":"2024-03-12","cited_by_count":20},{"id":"2302.11074","title":"Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks","created":"2023-02-22","cited_by_count":10},{"id":"2403.02756","title":"Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models","created":"2024-03-05","cited_by_count":10}],"next_cursor":null}