@inproceedings{TaesiriCVPR2024,

title = {GlitchBench: Can large multimodal models detect video game glitches?},

author = {Mohammad Reza Taesiri and Tianjun Feng and Anh Nguyen and Cor-Paul Bezemer},

year  = {2024},

date = {2024-06-15},

urldate = {2024-03-15},

booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

abstract = {Large multimodal models (LMMs) have evolved from

large language models (LLMs) to integrate multiple input

modalities, such as visual inputs. This integration augments

the capacity of LLMs for tasks requiring visual comprehen-

sion and reasoning. However, the extent and limitations of

their enhanced abilities are not fully understood, especially

when it comes to real-world tasks. To address this gap, we

introduce GlitchBench, a novel benchmark derived from

video game quality assurance tasks, to test and evaluate the

reasoning capabilities of LMMs. Our benchmark is curated

from a variety of unusual and glitched scenarios from video

games and aims to challenge both the visual and linguis-

tic reasoning powers of LMMs in detecting and interpreting

out-of-the-ordinary events. We evaluate multiple state-of-

the-art LMMs, and we show that GlitchBench presents a

new challenge for these models. Code and data are avail-

able at: https://glitchbench.github.io/},

keywords = {Computer games, Foundation models, Game development, Gameplay videos, LLM},

pubstate = {published},

tppubtype = {inproceedings}

}