EUVIMEDEUVIMED entdecken
Crossref

CLER: Improving Multimodal Financial Reasoning by Cross-MLLM Error Reflection

Shuangyan Deng, Zhongsheng Wang, Rui Mao, Ciprian Doru Giurcăneanu, Jiamou Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30494-30502

DOI: 10.1609/aaai.v40i36.40303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuangyan Deng und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in Multimodal Large Language Models (MLLMs) have enabled joint reasoning over financial textual and visual inputs. However, they still struggle with financial terminology, logical consistency, and numerical computations. Moreover, while commercial large models perform well on reasoning tasks, their high inference costs limit their scalable usage in real world financial applications. We thus propose a cost-effective framework, CLER, that combines contrastive retrieval with step-wise reflection to improve reasoning performance. Also, the reasoning cost is only generated in the test stage when using commercial large models. CLER leverages FinErrorSet, a dataset of 8,000+ mistake correction pairs from diverse open-source MLLMs. A fine grained retriever is trained to identify structurally relevant errors for self-correction through individual reflection. Experiments on three benchmarks show that CLER consistently outperforms other baselines. To our knowledge, CLER is the first framework to use cross-model errors for financial reasoning.

Zitieren

APA

Deng, S., Wang, Z., Mao, R., Giurcăneanu, C. D., & Liu, J. (2026). CLER: Improving Multimodal Financial Reasoning by Cross-MLLM Error Reflection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30494-30502. https://doi.org/10.1609/aaai.v40i36.40303

Vancouver

Deng S, Wang Z, Mao R, Giurcăneanu CD, Liu J. CLER: Improving Multimodal Financial Reasoning by Cross-MLLM Error Reflection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30494-30502. doi:10.1609/aaai.v40i36.40303

BibTeX
@article{Deng2026,
  author = {Deng, Shuangyan and Wang, Zhongsheng and Mao, Rui and Giurcăneanu, Ciprian Doru and Liu, Jiamou},
  title = {CLER: Improving Multimodal Financial Reasoning by Cross-MLLM Error Reflection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {36},
  pages = {30494--30502},
  doi = {10.1609/aaai.v40i36.40303}
}
Kostenlos starten →