Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling

Guangmin Zheng, Jin Wang, Xiaobing Zhou, Xuejie Zhang


Abstract
Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a question. Because of the hallucination issue, the generated soft negative rationales with high textual quality but illogical semantics do not always help improve answer accuracy. This study proposes a rationale generation method using soft negative sampling (SNSE-CoT) to mitigate hallucinations in multimodal CoT. Five methods were applied to generate soft negative samples that shared highly similar text but had different semantics from the original. Bidirectional margin loss (BML) was applied to introduce them into the traditional contrastive learning framework that involves only positive and negative samples. Extensive experiments on the ScienceQA dataset demonstrated the effectiveness of the proposed method. Code and data are released at https://github.com/zgMin/SNSE-CoT.
Anthology ID:
2024.lrec-main.537
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
6059–6076
Language:
URL:
https://aclanthology.org/2024.lrec-main.537
DOI:
Bibkey:
Cite (ACL):
Guangmin Zheng, Jin Wang, Xiaobing Zhou, and Xuejie Zhang. 2024. Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6059–6076, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling (Zheng et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.537.pdf