LLM embeddings from policy text outperform hand-engineered features in a GLM for French motor insurance claim frequency, with larger gains at small sample sizes and further improvement from insurance-specific fine-tuning.
arXiv preprint arXiv:2102.05784 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic insurance pricing with large language models
LLM embeddings from policy text outperform hand-engineered features in a GLM for French motor insurance claim frequency, with larger gains at small sample sizes and further improvement from insurance-specific fine-tuning.