Jing Jiang, Rui Cao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledgegeneration-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated knowledge for K-VQA in a zero-shot manner. We evaluate our method on two K-VQA benchmarks and found that our method performs better than previous zero-shot K-VQA methods and our generated knowledge is generally relevant and helpful. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.02541")
get_code_for_paper("2402.02541")
have("2402.02541")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.02541.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.02541)
Connect an agent — have() is free.