Pith. sign in

Lawrence Zitnick, and Devi Parikh

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension

cs.CV · 2024-12-16 · conditional · novelty 6.0

PunchBench, a 54,000-question benchmark spanning cartoons, posts, comments, and memes, shows that multimodal LLMs lag humans in punchline comprehension, and its Simple-to-Complex Chain-of-Question prompt yields small accuracy gains.

citing papers explorer

Showing 1 of 1 citing paper.

  • PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension cs.CV · 2024-12-16 · conditional · none · ref 4

    PunchBench, a 54,000-question benchmark spanning cartoons, posts, comments, and memes, shows that multimodal LLMs lag humans in punchline comprehension, and its Simple-to-Complex Chain-of-Question prompt yields small accuracy gains.