A causal framework with latent mediators quantifies how prompt modalities affect code LLMs, finding that input-output examples and function-header names are influential beyond natural language instructions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CodeSCM: Causal Analysis for Multi-Modal Code Generation
A causal framework with latent mediators quantifies how prompt modalities affect code LLMs, finding that input-output examples and function-header names are influential beyond natural language instructions.