Swapping named entities between embedding-similar chunks of earnings call transcripts lowers LLM company-identification accuracy on the swapped chunks from about 90% to about 60%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Named Entity Swapping for Metadata Anonymization in a Text Corpus
Swapping named entities between embedding-similar chunks of earnings call transcripts lowers LLM company-identification accuracy on the swapped chunks from about 90% to about 60%.