{"list":"other","total":71,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"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":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"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":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2409.12917","title":"Training Language Models to Self-Correct via Reinforcement Learning","created":"2024-09-19","cited_by_count":426},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2311.16452","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","created":"2023-11-28","cited_by_count":329},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301},{"id":"2304.08247","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","created":"2023-04-14","cited_by_count":286},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205},{"id":"2406.19280","title":"HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale","created":"2024-06-27","cited_by_count":200},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"2308.07921","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","created":"2023-08-15","cited_by_count":166},{"id":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144},{"id":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143},{"id":"2409.18486","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","created":"2024-09-27","cited_by_count":127},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2402.11436","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","created":"2024-02-18","cited_by_count":114},{"id":"2402.10963","title":"GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements","created":"2024-02-13","cited_by_count":103},{"id":"2308.04592","title":"Shepherd: A Critic for Language Model Generation","created":"2023-08-08","cited_by_count":97},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94},{"id":"2311.09774","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","created":"2023-11-16","cited_by_count":92},{"id":"2306.03030","title":"Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset","created":"2023-06-05","cited_by_count":91},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"id":"2412.00154","title":"o1-Coder: an o1 Replication for Coding","created":"2024-11-29","cited_by_count":78},{"id":"2303.16749","title":"Improving Code Generation by Training with Natural Language Feedback","created":"2023-03-28","cited_by_count":76},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67},{"id":"2404.14779","title":"Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches","created":"2024-04-23","cited_by_count":52},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50},{"id":"2305.14497","title":"Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement","created":"2023-05-23","cited_by_count":43},{"id":"2407.13301","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis","created":"2024-07-18","cited_by_count":43},{"id":"2406.14024","title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback","created":"2024-06-20","cited_by_count":41},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33},{"id":"2408.16326","title":"Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic","created":"2024-08-29","cited_by_count":28},{"id":"2411.03590","title":"From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond","created":"2024-11-06","cited_by_count":24},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17},{"id":"2411.14461","title":"Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios","created":"2024-11-16","cited_by_count":10}],"next_cursor":null}