Introduces Ex-ToxiCN-MM dataset and RIKE framework (with AKE and RIR modules) that outperforms baselines on attributing harm in ambiguous Chinese memes using C-HarmKB.
arXiv preprint arXiv:2305.17678 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A retrieval-augmented zero-shot framework acquires open-web knowledge to improve understanding and detection of recent evolving memes over baselines.
citing papers explorer
-
Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes
Introduces Ex-ToxiCN-MM dataset and RIKE framework (with AKE and RIR modules) that outperforms baselines on attributing harm in ambiguous Chinese memes using C-HarmKB.
-
I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition
A retrieval-augmented zero-shot framework acquires open-web knowledge to improve understanding and detection of recent evolving memes over baselines.