Long Story Short: a Summarize-then-Search Method for Long Video Question Answering. (arXiv:2311.01233v1 [cs.CV])

Large language models such as GPT-3 have demonstrated an impressive
capability to adapt to new tasks without requiring task-specific training data.
This capability has been particularly effective in settings such as narrative
question answering, where the diversity of tasks is immense, but the available
supervision data is small. In this work, we investigate if such language models
can extend their zero-shot reasoning abilities to long multimodal narratives in
multimedia content such as drama, movies, and animation, where the story plays …

adapt arxiv capability data diversity gpt gpt-3 language language models large language large language models narrative question answering search story supervision tasks task-specific training training training data video