A local open-weight LLM toolchain transforms sensitive Swedish court decisions into anonymized English summaries and embeddings that retain semantic content, validated on 10,842 LVM documents and a suicide-related content prediction task.
Efficient es- timation of word representations in vector space
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Transforming Sensitive Documents into Quantitative Data: An AI-Based Preprocessing Toolchain for Structured and Privacy-Conscious Analysis
A local open-weight LLM toolchain transforms sensitive Swedish court decisions into anonymized English summaries and embeddings that retain semantic content, validated on 10,842 LVM documents and a suicide-related content prediction task.