Synthetic Q/A pairs generated by DeepSeek-V3 from EDA documents, combined with RAFT fine-tuning, improve retrieval-augmented EDA assistant accuracy, with real-user few-shot examples further helping on human-style questions.
Eda corpus: A large language model dataset for enhanced interaction with openroad,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving LLM-Powered EDA Assistants with RAFT
Synthetic Q/A pairs generated by DeepSeek-V3 from EDA documents, combined with RAFT fine-tuning, improve retrieval-augmented EDA assistant accuracy, with real-user few-shot examples further helping on human-style questions.