LLM prompting for DSM modularization reaches near-reference quality in 30 iterations on five cases with three models, but domain knowledge impairs performance on complex DSMs, leading to the semantic-alignment hypothesis.
Factored dependency structure matrix for representation of multi-connection systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Cost-Aware SGD samples by gradient-norm-to-cost ratio and is instantiated as Cost-Aware GRPO for length-dependent policy gradients, reducing tokens used in LLM RL while matching baseline accuracy.
citing papers explorer
-
Design Structure Matrix Modularization with Large Language Models
LLM prompting for DSM modularization reaches near-reference quality in 30 iterations on five cases with three models, but domain knowledge impairs performance on complex DSMs, leading to the semantic-alignment hypothesis.
-
Cost-Aware Learning
Cost-Aware SGD samples by gradient-norm-to-cost ratio and is instantiated as Cost-Aware GRPO for length-dependent policy gradients, reducing tokens used in LLM RL while matching baseline accuracy.