DecoRTL combines token-class-aware temperature adjustment with contrastive top-K reranking to improve synthesizability and functional correctness of LLM-generated Verilog.
Hot or cold? adaptive temperature sampling for code generation with large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.PL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs
DecoRTL combines token-class-aware temperature adjustment with contrastive top-K reranking to improve synthesizability and functional correctness of LLM-generated Verilog.