{"list":"other","total":73,"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":"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":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461},{"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":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"2410.18982","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","created":"2024-10-08","cited_by_count":143},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117},{"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":"2410.15553","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","created":"2024-10-21","cited_by_count":102},{"id":"2411.16489","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","created":"2024-11-25","cited_by_count":92},{"id":"2402.18667","title":"FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability","created":"2024-02-28","cited_by_count":80},{"id":"2405.11143","title":"OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework","created":"2024-05-20","cited_by_count":73},{"id":"2406.13542","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","created":"2024-06-19","cited_by_count":73},{"id":"2305.13068","title":"Making Language Models Better Tool Learners with Execution Feedback","created":"2023-05-22","cited_by_count":70},{"id":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":68},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","cited_by_count":67},{"id":"2407.01509","title":"MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs","created":"2024-07-01","cited_by_count":62},{"id":"2502.08745","title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy","created":"2025-02-12","cited_by_count":53},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35},{"id":"2501.06458","title":"O1 Replication Journey -- Part 3: Inference-time Scaling for Medical Reasoning","created":"2025-01-11","cited_by_count":35},{"id":"2402.14334","title":"INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models","created":"2024-02-22","cited_by_count":33},{"id":"2411.07037","title":"LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios","created":"2024-11-11","cited_by_count":33},{"id":"2411.06208","title":"IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization","created":"2024-11-09","cited_by_count":31},{"id":"2502.14494","title":"StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following","created":"2025-02-20","cited_by_count":29},{"id":"2404.02823","title":"Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models","created":"2024-04-03","cited_by_count":27},{"id":"2404.15846","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","created":"2024-04-24","cited_by_count":27},{"id":"2407.08440","title":"Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models","created":"2024-07-11","cited_by_count":23},{"id":"2412.11605","title":"SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models","created":"2024-12-16","cited_by_count":23},{"id":"2404.02575","title":"Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models","created":"2024-04-03","cited_by_count":20},{"id":"2502.19166","title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","created":"2025-02-26","cited_by_count":19},{"id":"2502.04153","title":"UltraIF: Advancing Instruction Following from the Wild","created":"2025-02-06","cited_by_count":18},{"id":"2502.04498","title":"Verifiable Format Control for Large Language Model Generations","created":"2025-02-06","cited_by_count":17},{"id":"2502.04688","title":"M-IFEval: Multilingual Instruction-Following Evaluation","created":"2025-02-07","cited_by_count":17},{"id":"2311.09829","title":"FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models","created":"2023-11-16","cited_by_count":12},{"id":"2501.04945","title":"Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models","created":"2025-01-09","cited_by_count":12},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12},{"id":"2502.17204","title":"Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following","created":"2025-02-24","cited_by_count":12},{"id":"2402.13109","title":"CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models","created":"2024-02-20","cited_by_count":11},{"id":"2410.09412","title":"FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback","created":"2024-10-12","cited_by_count":11},{"id":"2410.24175","title":"Constraint Back-translation Improves Complex Instruction Following of Large Language Models","created":"2024-10-31","cited_by_count":11},{"id":"2503.06573","title":"WildIFEval: Instruction Following in the Wild","created":"2025-03-09","cited_by_count":11},{"id":"2503.07539","title":"XIFBench: Evaluating Large Language Models on Multilingual Instruction Following","created":"2025-03-10","cited_by_count":11},{"id":"2502.17787","title":"AIR: Complex Instruction Generation via Automatic Iterative Refinement","created":"2025-02-25","cited_by_count":10},{"id":"2402.11532","title":"Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models","created":"2024-02-18","cited_by_count":9},{"id":"2410.09584","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","created":"2024-10-12","cited_by_count":9},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8},{"id":"2406.11301","title":"Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants","created":"2024-06-17","cited_by_count":3},{"id":"2410.06089","title":"TOWER: Tree Organized Weighting for Evaluating Complex Instructions","created":"2024-10-08","cited_by_count":1}],"next_cursor":null}