Using GLES survey data, the paper shows Llama2 produces synthetic German opinions closer to real responses than Gemma or Mixtral, with a consistent left-party bias.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
Using GLES survey data, the paper shows Llama2 produces synthetic German opinions closer to real responses than Gemma or Mixtral, with a consistent left-party bias.