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.
Title resolution pending
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
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.