Can Multimodal Large Language Model Think Analogically?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912102825852928 |
|---|---|
| author | Guo, Diandian Cao, Cong Yuan, Fangfang Wang, Dakui Ma, Wei Liu, Yanbing Fu, Jianhui |
| author_facet | Guo, Diandian Cao, Cong Yuan, Fangfang Wang, Dakui Ma, Wei Liu, Yanbing Fu, Jianhui |
| contents | Analogical reasoning, particularly in multimodal contexts, is the foundation of human perception and creativity. Multimodal Large Language Model (MLLM) has recently sparked considerable discussion due to its emergent capabilities. In this paper, we delve into the multimodal analogical reasoning capability of MLLM. Specifically, we explore two facets: \textit{MLLM as an explainer} and \textit{MLLM as a predictor}. In \textit{MLLM as an explainer}, we primarily focus on whether MLLM can deeply comprehend multimodal analogical reasoning problems. We propose a unified prompt template and a method for harnessing the comprehension capabilities of MLLM to augment existing models. In \textit{MLLM as a predictor}, we aim to determine whether MLLM can directly solve multimodal analogical reasoning problems. The experiments show that our approach outperforms existing methods on popular datasets, providing preliminary evidence for the analogical reasoning capability of MLLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01307 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can Multimodal Large Language Model Think Analogically? Guo, Diandian Cao, Cong Yuan, Fangfang Wang, Dakui Ma, Wei Liu, Yanbing Fu, Jianhui Computation and Language Analogical reasoning, particularly in multimodal contexts, is the foundation of human perception and creativity. Multimodal Large Language Model (MLLM) has recently sparked considerable discussion due to its emergent capabilities. In this paper, we delve into the multimodal analogical reasoning capability of MLLM. Specifically, we explore two facets: \textit{MLLM as an explainer} and \textit{MLLM as a predictor}. In \textit{MLLM as an explainer}, we primarily focus on whether MLLM can deeply comprehend multimodal analogical reasoning problems. We propose a unified prompt template and a method for harnessing the comprehension capabilities of MLLM to augment existing models. In \textit{MLLM as a predictor}, we aim to determine whether MLLM can directly solve multimodal analogical reasoning problems. The experiments show that our approach outperforms existing methods on popular datasets, providing preliminary evidence for the analogical reasoning capability of MLLM. |
| title | Can Multimodal Large Language Model Think Analogically? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.01307 |