The authors present a multilingual vocabulary and a detection tool using string matching, NER and LLM disambiguation that flags and contextualizes harmful language in cultural heritage metadata, reporting 87 percent precision.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections
The authors present a multilingual vocabulary and a detection tool using string matching, NER and LLM disambiguation that flags and contextualizes harmful language in cultural heritage metadata, reporting 87 percent precision.