A self-validating and self-correcting LLM framework raises testbench generation pass rate to 70.13%, up from 52.18% for the prior AutoBench framework.
Stimulus Generation for Con- strained Random Simulation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design
A self-validating and self-correcting LLM framework raises testbench generation pass rate to 70.13%, up from 52.18% for the prior AutoBench framework.