Towards Low-Resource Harmful Meme Detection with LMM Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909380506550272 |
|---|---|
| author | Huang, Jianzhao Lin, Hongzhan Liu, Ziyan Luo, Ziyang Chen, Guang Ma, Jing |
| author_facet | Huang, Jianzhao Lin, Hongzhan Liu, Ziyan Luo, Ziyang Chen, Guang Ma, Jing |
| contents | The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled examples are available. In this paper, we propose an agency-driven framework for low-resource harmful meme detection, employing both outward and inward analysis with few-shot annotated samples. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first retrieve relative memes with annotations to leverage label information as auxiliary signals for the LMM agent. Then, we elicit knowledge-revising behavior within the LMM agent to derive well-generalized insights into meme harmfulness. By combining these strategies, our approach enables dialectical reasoning over intricate and implicit harm-indicative patterns. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05383 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Low-Resource Harmful Meme Detection with LMM Agents Huang, Jianzhao Lin, Hongzhan Liu, Ziyan Luo, Ziyang Chen, Guang Ma, Jing Computation and Language The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few labeled examples are available. In this paper, we propose an agency-driven framework for low-resource harmful meme detection, employing both outward and inward analysis with few-shot annotated samples. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first retrieve relative memes with annotations to leverage label information as auxiliary signals for the LMM agent. Then, we elicit knowledge-revising behavior within the LMM agent to derive well-generalized insights into meme harmfulness. By combining these strategies, our approach enables dialectical reasoning over intricate and implicit harm-indicative patterns. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task. |
| title | Towards Low-Resource Harmful Meme Detection with LMM Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.05383 |