Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes

Yosuke Miyanishi, Minh Le Nguyen


Abstract
Amidst the rapid expansion of Machine Learning (ML) and Large Language Models (LLMs), understanding the semantics within their mechanisms is vital. Causal analyses define semantics, while gradient-based methods are essential to eXplainable AI (XAI), interpreting the model’s ‘black box’. Integrating these, we investigate how a model’s mechanisms reveal its causal effect on evidence-based decision-making. Research indicates intersectionality - the combined impact of an individual’s demographics - can be framed as an Average Treatment Effect (ATE). This paper demonstrates that hateful meme detection can be viewed as an ATE estimation using intersectionality principles, and summarized gradient-based attention scores highlight distinct behaviors of three Transformer models. We further reveal that LLM Llama-2 can discern the intersectional aspects of the detection through in-context learning and that the learning process could be explained via meta-gradient, a secondary form of gradient. In conclusion, this work furthers the dialogue on Causality and XAI. Our code is available online (see External Resources section).
Anthology ID:
2024.lrec-main.259
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:
2901–2916
Language:
URL:
https://aclanthology.org/2024.lrec-main.259
DOI:
Bibkey:
Cite (ACL):
Yosuke Miyanishi and Minh Le Nguyen. 2024. Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2901–2916, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes (Miyanishi & Nguyen, LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.259.pdf