analiza aiqbench
This paper introduces a zero-shot framework that dynamically retrieves open-web evidence to interpret evolving multimodal memes, addressing the limitations of static parametric knowledge in pretrained models. By synthesizing external background information, the approach significantly improves knowledge recovery and detection performance on recent datasets spanning 2024 to 2026. The work establishes a new benchmark for meme understanding, offering a practical solution for systems requiring up-to-date contextual awareness in open-world scenarios.
I Know What You Meme, Even If it Emerged Today: Understanding Evolving Memes through Open-World Knowledge Acquisition
arXiv:2606.05316v1 Announce Type: new Abstract: Multimodal memes are dynamic and often require up to date background knowledge for interpretation. Existing methods often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes. We introduce Query Retrieve Conclude, a zero shot framework that identifies missing knowledge, retrieves open web evidence, and synthesizes evidence grounded background knowledge for meme understanding and detection. We also introduce a curated meme understanding benchmark of recent memes from 2024 to 2026 with external background knowledge annotations. Experiments on three meme understanding datasets and five meme detection tasks show that our framework improves knowledge recovery, meme understanding and downstream detection over zero shot baselines.
Abstract:Multimodal memes are dynamic and often require up to date background knowledge for interpretation. Existing methods often overlook such knowledge or rely on fixed parametric knowledge of pretrained models that may be incomplete, outdated, or unavailable for emerging memes. We introduce Query Retrieve Conclude, a zero shot framework that identifies missing knowledge, retrieves open web evidence, and synthesizes evidence grounded background knowledge for meme understanding and detection. We also introduce a curated meme understanding benchmark of recent memes from 2024 to 2026 with external background knowledge annotations. Experiments on three meme understanding datasets and five meme detection tasks show that our framework improves knowledge recovery, meme understanding and downstream detection over zero shot baselines.
Artificial Intelligence (cs.AI)
arXiv:2606.05316 [cs.AI]
(or arXiv:2606.05316v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.05316 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 208 cuvinte
Subiecte conexe
Tracing Morphology, Semantics, and Divergence in Language Acquisition
arXiv · 15 oct. 2026
From the Gettier Machine to Justified True Output: A Three-Step Account of Rational Trust in Generative AI
arXiv · 31 oct. 2026
Fast-SDE: Efficient Single-Microphone Sound Source Distance Estimation in Reverberant Environments
arXiv · 11 iun. 2026
Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs
arXiv · 28 iul. 2026