{"list":"other","total":55,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"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":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"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":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2301.07597","title":"How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection","created":"2023-01-18","cited_by_count":481},{"id":"2308.01825","title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","created":"2023-08-03","cited_by_count":427},{"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":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"1904.01557","title":"Analysing Mathematical Reasoning Abilities of Neural Models","created":"2019-04-02","cited_by_count":335},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2504.16891","title":"AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset","created":"2025-04-23","cited_by_count":174},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126},{"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":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"2306.01684","title":"Harnessing large-language models to generate private synthetic text","created":"2023-06-02","cited_by_count":65},{"id":"2506.01716","title":"Self-Challenging Language Model Agents","created":"2025-06-02","cited_by_count":59},{"id":"2411.04109","title":"Self-Consistency Preference Optimization","created":"2024-11-06","cited_by_count":50},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36},{"id":"2506.04689","title":"Recycling the Web: A Method to Enhance Pre-training Data Quality and Quantity for Language Models","created":"2025-06-05","cited_by_count":31},{"id":"2409.08239","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","created":"2024-09-12","cited_by_count":28},{"id":"2406.00770","title":"Automatic Instruction Evolving for Large Language Models","created":"2024-06-02","cited_by_count":26},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25},{"id":"2402.14158","title":"TOOLVERIFIER: Generalization to New Tools via Self-Verification","created":"2024-02-21","cited_by_count":24},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15},{"id":"2501.18578","title":"R.I.P.: Better Models by Survival of the Fittest Prompts","created":"2025-01-30","cited_by_count":13}],"next_cursor":null}