Most tested LLMs excuse colour errors that people consider highly severe, while both groups penalize gender errors; only one model, Doubao, reproduced the human severity ordering.
Room for improvement in automatic image description: an error analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In recent years we have seen rapid and significant progress in automatic image description but what are the open problems in this area? Most work has been evaluated using text-based similarity metrics, which only indicate that there have been improvements, without explaining what has improved. In this paper, we present a detailed error analysis of the descriptions generated by a state-of-the-art attention-based model. Our analysis operates on two levels: first we check the descriptions for accuracy, and then we categorize the types of errors we observe in the inaccurate descriptions. We find only 20% of the descriptions are free from errors, and surprisingly that 26% are unrelated to the image. Finally, we manually correct the most frequently occurring error types (e.g. gender identification) to estimate the performance reward for addressing these errors, observing gains of 0.2--1 BLEU point per type.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Large Language Models Judge Error Severity Like Humans?
Most tested LLMs excuse colour errors that people consider highly severe, while both groups penalize gender errors; only one model, Doubao, reproduced the human severity ordering.