{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:22:36Z","timestamp":1783149756620,"version":"3.54.6"},"reference-count":53,"publisher":"Elsevier BV","issue":"8","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242025K30024"],"award-info":[{"award-number":["2242025K30024"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008081","name":"Southeast University","doi-asserted-by":"publisher","award":["RF1028623234"],"award-info":[{"award-number":["RF1028623234"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376057"],"award-info":[{"award-number":["62376057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.ipm.2026.104952","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T04:09:17Z","timestamp":1780978157000},"page":"104952","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Boosting multimodal CoT reasoning through DPO with Error-prone Sample Synthesis"],"prefix":"10.1016","volume":"63","author":[{"given":"Yuhang","family":"Lou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7352-1710","authenticated-orcid":false,"given":"Wenjun","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3238-5884","authenticated-orcid":false,"given":"Yao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8782-857X","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengyuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104952_b1","series-title":"Fine-tuning pre-trained transformer language models to distantly supervised relation extraction","author":"Alt","year":"2019"},{"key":"10.1016\/j.ipm.2026.104952_b2","series-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b3","series-title":"Are we on the right way for evaluating large vision-language models?","author":"Chen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b4","series-title":"M3CoT: A novel benchmark for multi-domain multi-step multi-modal chain-of-thought","author":"Chen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b5","series-title":"MINT-CoT: Enabling interleaved visual tokens in mathematical chain-of-thought reasoning","author":"Chen","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b6","series-title":"Revisiting chain-of-thought prompting: Zero-shot can be stronger than few-shot","author":"Cheng","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b7","series-title":"AAAI Conference on Artificial Intelligence","article-title":"CoMT: A novel benchmark for chain of multi-modal understanding and reasoning","author":"Cheng","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b8","series-title":"CHiP: Cross-modal hierarchical direct preference optimization for multimodal LLMs","author":"Fu","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b9","series-title":"Findings of the association for computational linguistics: ACL 2025","first-page":"16563","article-title":"Mitigating hallucination in multimodal large language model via hallucination-targeted direct preference optimization","author":"Fu","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b10","doi-asserted-by":"crossref","unstructured":"Gao, T., Chen, P., Zhang, M., Fu, C., Shen, Y., Zhang, Y., Zhang, S., Zheng, X., Sun, X., Cao, L., et al. (2024). Cantor: Inspiring multimodal chain-of-thought of mllm. In Proceedings of the 32nd ACM international conference on multimedia (pp. 9096\u20139105).","DOI":"10.1145\/3664647.3681249"},{"key":"10.1016\/j.ipm.2026.104952_b11","series-title":"A comparison of DeepSeek and other LLMs","author":"Gao","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b12","series-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b13","series-title":"A survey on progress in LLM alignment from the perspective of reward design","author":"Ji","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b14","series-title":"MME-CoT: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b15","series-title":"Proceedings of the 2024 conference of the North American chapter of the association for computational linguistics: human language technologies (volume 1: long papers)","first-page":"2262","article-title":"Program-aided reasoners (better) know what they know","author":"Kabra","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b16","series-title":"Process reward models that think","author":"Khalifa","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b17","series-title":"Training language models to self-correct via reinforcement learning","author":"Kumar","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b18","series-title":"Comat: Chain of mathematically annotated thought improves mathematical reasoning","author":"Leang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b19","series-title":"Volcano: Mitigating multimodal hallucination through self-feedback guided revision","author":"Lee","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b20","series-title":"CoT-RAG: Integrating chain of thought and retrieval-augmented generation to enhance reasoning in large language models","author":"Li","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b21","series-title":"Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: long papers)","first-page":"14188","article-title":"Multi-modal preference alignment remedies degradation of visual instruction tuning on language models","author":"Li","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b22","series-title":"Imagegen-cot: Enhancing text-to-image in-context learning with chain-of-thought reasoning","author":"Liao","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b23","series-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b24","series-title":"A survey of direct preference optimization","author":"Liu","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b25","unstructured":"Lu, P., Bansal, H., Xia, T., Liu, J., Li, C., Hajishirzi, H., Cheng, H., Chang, K. W., Galley, M., & Gao, J. (2024). MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts. In International conference on learning representations."},{"key":"10.1016\/j.ipm.2026.104952_b26","doi-asserted-by":"crossref","unstructured":"Lu, P., Mishra, S., Xia, T., Qiu, L., Chang, K. W., Zhu, S. C., Tafjord, O., Clark, P., & Kalyan, A. (2022). Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering. In The 36th conference on neural information processing systems (neurIPS).","DOI":"10.52202\/068431-0182"},{"key":"10.1016\/j.ipm.2026.104952_b27","doi-asserted-by":"crossref","first-page":"43447","DOI":"10.52202\/075280-1882","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","author":"Lu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104952_b28","series-title":"Self-refine: Iterative refinement with self-feedback","author":"Madaan","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b29","doi-asserted-by":"crossref","first-page":"53728","DOI":"10.52202\/075280-2338","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104952_b30","series-title":"Proceedings of the 2024 conference on empirical methods in natural language processing","first-page":"12171","article-title":"Empowering multi-step reasoning across languages via program-aided language models","author":"Ranaldi","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b31","doi-asserted-by":"crossref","first-page":"8612","DOI":"10.52202\/079017-0275","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume":"37","author":"Shao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104952_b32","series-title":"Math-llava: Bootstrapping mathematical reasoning for multimodal large language models","author":"Shi","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b33","series-title":"Reflexion: Language agents with verbal reinforcement learning","author":"Shinn","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b34","series-title":"Stop overthinking: A survey on efficient reasoning for large language models","author":"Sui","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b35","series-title":"Mm-verify: Enhancing multimodal reasoning with chain-of-thought verification","author":"Sun","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b36","series-title":"Solving math word problems with process- and outcome-based feedback","author":"Uesato","year":"2022"},{"key":"10.1016\/j.ipm.2026.104952_b37","series-title":"T-SciQ: Teaching multimodal chain-of-thought reasoning via mixed large language model signals for science question answering","author":"Wang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b38","series-title":"Thinking short and right over thinking long: Serving LLM reasoning efficiently and accurately","author":"Wang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b39","doi-asserted-by":"crossref","first-page":"95095","DOI":"10.52202\/079017-3014","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104952_b40","series-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b41","series-title":"mDPO: Conditional preference optimization for multimodal large language models","author":"Wang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b42","series-title":"Llava-cot: Let vision language models reason step-by-step","author":"Xu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b43","series-title":"Task preference optimization: Improving multimodal large language models with vision task alignment","author":"Yan","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b44","series-title":"R1-onevision: Advancing generalized multimodal reasoning through cross-modal formalization","author":"Yang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b45","series-title":"RLHF-V: Towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback","author":"Yu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b46","doi-asserted-by":"crossref","unstructured":"Yue, X., Ni, Y., Zhang, K., Zheng, T., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., Sun, Y., et al. (2024). Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9556\u20139567).","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"10.1016\/j.ipm.2026.104952_b47","series-title":"R1-vl: Learning to reason with multimodal large language models via step-wise group relative policy optimization","author":"Zhang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b48","series-title":"European conference on computer vision","first-page":"169","article-title":"Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104952_b49","series-title":"BELLE: A bi-level multi-agent reasoning framework for multi-hop question answering","author":"Zhang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b50","series-title":"Arise: Towards knowledge-augmented reasoning via risk-adaptive search","author":"Zhang","year":"2025"},{"key":"10.1016\/j.ipm.2026.104952_b51","series-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104952_b52","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Lu, Y., Kim, M. J., Fu, Z., Zhang, Z., Wu, Y., Li, Z., Ma, Q., Han, S., Finn, C., et al. (2025). Cot-vla: Visual chain-of-thought reasoning for vision-language-action models. In Proceedings of the computer vision and pattern recognition conference (pp. 1702\u20131713).","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"10.1016\/j.ipm.2026.104952_b53","doi-asserted-by":"crossref","first-page":"5168","DOI":"10.52202\/075280-0228","article-title":"Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003432?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003432?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:09:47Z","timestamp":1783148987000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326003432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":53,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["S0306457326003432"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104952","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Boosting multimodal CoT reasoning through DPO with Error-prone Sample Synthesis","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104952","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104952"}}