Boosting multimodal CoT reasoning through DPO with Error-prone Sample Synthesis.
Yuhang Lou|Wenjun Ke|Yao He|Peng Wang|Qi Liu|Hengyuan Xu
| Anthology ID: | DBLP:journals/ipm/LouKHWLX26 |
|---|---|
| Year: | 2026 |
| Venue: | Information Processing and Management |
| Pages: | 104952 |
| URL: | https://doi.org/10.1016/J.IPM.2026.104952 |
| DOI: | https://doi.org/10.1016/J.IPM.2026.104952 |
| DBLP: | journals/ipm/LouKHWLX26 |
| BibTeX: |
@article{lou-2026-boosting,
author = {Yuhang Lou and
Wenjun Ke and
Yao He and
Peng Wang and
Qi Liu and
Hengyuan Xu},
title = {{Boosting multimodal CoT reasoning through DPO with Error-prone Sample Synthesis}},
journal = {Information Processing and Management},
volume = {63},
number = {8},
pages = {104952},
year = {2026},
url = {https://doi.org/10.1016/J.IPM.2026.104952},
doi = {https://doi.org/10.1016/J.IPM.2026.104952}
}