A multi-LLM weighted penalty added to score-based causal discovery gives inconsistent gains on five small benchmarks, with several results worse than the unmodified baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
A multi-LLM weighted penalty added to score-based causal discovery gives inconsistent gains on five small benchmarks, with several results worse than the unmodified baseline.