They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911419957510144 |
|---|---|
| author | Tripathi, Sahil Kashyap, Gautam Siddharth Nasim, Mehwish Yang, Jian Gao, Jiechao Naseem, Usman |
| author_facet | Tripathi, Sahil Kashyap, Gautam Siddharth Nasim, Mehwish Yang, Jian Gao, Jiechao Naseem, Usman |
| contents | Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusion-based methods to in-context learning with Large Vision-Language Models (LVLMs), have made progress but remain limited by three factors: i) cultural blindness (missing symbolic context), ii) boundary ambiguity (satire vs. abuse confusion), and iii) lack of interpretability (opaque model reasoning). We introduce CROSS-ALIGN+, a three-stage framework that systematically addresses these limitations: (1) Stage I mitigates cultural blindness by enriching multimodal representations with structured knowledge from ConceptNet, Wikidata, and Hatebase; (2) Stage II reduces boundary ambiguity through parameter-efficient LoRA adapters that sharpen decision boundaries; and (3) Stage III enhances interpretability by generating cascaded explanations. Extensive experiments on five benchmarks and eight LVLMs demonstrate that CROSS-ALIGN+ consistently outperforms state-of-the-art methods, achieving up to 17% relative F1 improvement while providing interpretable justifications for each decision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03822 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References Tripathi, Sahil Kashyap, Gautam Siddharth Nasim, Mehwish Yang, Jian Gao, Jiechao Naseem, Usman Computation and Language Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusion-based methods to in-context learning with Large Vision-Language Models (LVLMs), have made progress but remain limited by three factors: i) cultural blindness (missing symbolic context), ii) boundary ambiguity (satire vs. abuse confusion), and iii) lack of interpretability (opaque model reasoning). We introduce CROSS-ALIGN+, a three-stage framework that systematically addresses these limitations: (1) Stage I mitigates cultural blindness by enriching multimodal representations with structured knowledge from ConceptNet, Wikidata, and Hatebase; (2) Stage II reduces boundary ambiguity through parameter-efficient LoRA adapters that sharpen decision boundaries; and (3) Stage III enhances interpretability by generating cascaded explanations. Extensive experiments on five benchmarks and eight LVLMs demonstrate that CROSS-ALIGN+ consistently outperforms state-of-the-art methods, achieving up to 17% relative F1 improvement while providing interpretable justifications for each decision. |
| title | They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.03822 |