{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:25Z","timestamp":1763191105069,"version":"3.45.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227254","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["RFPO: Enhancing Mathematical Reasoning of Large Language Models with Fine-Grained Preference Optimization"],"prefix":"10.1109","author":[{"given":"Fei","family":"Gao","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"journal-title":"Language models are few-shot learners","year":"2020","author":"Brown","key":"ref1"},{"journal-title":"Lamda: Language models for dialog applications","year":"2022","author":"Thoppilan","key":"ref2"},{"journal-title":"Challenges and applications of large language models","year":"2023","author":"Kaddour","key":"ref3"},{"journal-title":"Voyager: An open-ended embodied agent with large language models","year":"2023","author":"Wang","key":"ref4"},{"journal-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","year":"2023","author":"Bubeck","key":"ref5"},{"journal-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref6"},{"volume":"17","volume-title":"Advances in neural information processing systems 17: proceedings of the 2004 conference","author":"Saul","key":"ref7"},{"key":"ref8","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Fine-tuning language models from human preferences","year":"2019","author":"Ziegler","key":"ref10"},{"key":"ref11","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"4447","article-title":"A general theoretical paradigm to understand learning from human preferences","volume-title":"Proc. Int. Conf. Artif. Intell. Stat","author":"Azar"},{"journal-title":"Kto: Model alignment as prospect theoretic optimization","year":"2024","author":"Ethayarajh","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.297"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3946"},{"journal-title":"Training verifiers to solve math word problems","year":"2021","author":"Cobbe","key":"ref17"},{"journal-title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","year":"2024","author":"Lai","key":"ref18"},{"journal-title":"Token-level Direct Preference Optimization","year":"2024","author":"Zeng","key":"ref19"},{"journal-title":"Iterative reasoning preference optimization","year":"2024","author":"Pang","key":"ref20"},{"journal-title":"Measuring mathematical problem solving with the math dataset","year":"2021","author":"Hendrycks","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref23","volume-title":"Categorical data analysis","volume":"792","author":"Agresti","year":"2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v048.i09"},{"journal-title":"Qwen2 technical report","year":"2024","author":"Yang","key":"ref26"},{"journal-title":"V-star: Training verifiers for self-taught reasoners","year":"2024","author":"Hosseini","key":"ref27"},{"key":"ref28","first-page":"15476","article-title":"Star: Bootstrapping reasoning with reasoning","volume":"35","author":"Zelikman","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"journal-title":"Smaug: Fixing failure modes of preference optimisation with DPO-positive","year":"2024","author":"Pal","key":"ref30"},{"key":"ref31","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Self-consistency improves chain of thought reasoning in language models","year":"2022","author":"Wang","key":"ref32"},{"journal-title":"Least-to-most prompting enables complex reasoning in large language models","year":"2022","author":"Zhou","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.147"},{"journal-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","year":"2022","author":"Chen","key":"ref35"},{"key":"ref36","first-page":"10764","article-title":"PAL: Program-aided language models","volume-title":"International Conference on Machine Learning","author":"Gao"},{"key":"ref37","first-page":"15476","article-title":"STAR: Bootstrapping reasoning with reasoning","volume":"35","author":"Zelikman","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Quiet-STAR: Language models can teach themselves to think before speaking","year":"2024","author":"Zelikman","key":"ref38"},{"journal-title":"V-STAR: Training verifiers for self-taught reasoners","year":"2024","author":"Hosseini","key":"ref39"},{"journal-title":"Scaling relationship on learning mathematical reasoning with large language models","year":"2023","author":"Yuan","key":"ref40"},{"journal-title":"Meta-math: Bootstrap your own mathematical questions for large language models","year":"2023","author":"Yu","key":"ref41"},{"journal-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","year":"2023","author":"Xuo","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.551"},{"journal-title":"Mammoth2: Scaling instructions from the web","year":"2024","author":"Yue","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.569"},{"journal-title":"Internlm-math: Open math large language models toward verifiable reasoning","year":"2024","author":"Ying","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"journal-title":"Let\u2019s verify step by step","year":"2023","author":"Lightman","key":"ref48"},{"journal-title":"Improving large language model fine-tuning for solving math problems","year":"2023","author":"Liu","key":"ref49"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227254.pdf?arnumber=11227254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:15:37Z","timestamp":1763190937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227254","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}