VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction
This addresses debugging for Verilog programmers, offering a substantial improvement over existing methods, though it appears incremental as it builds on LLM-based debugging approaches.
The paper tackles automated debugging of Verilog hardware description language by introducing VeriDebug, which integrates contrastive embedding and guided correction to unify bug detection and correction. The model achieves 64.7% accuracy in bug fixing, significantly outperforming existing open-source SOTAs (11.3%) and GPT-3.5-turbo (36.6%).
Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to Verilog debugging remains insufficiently explored. Here, we present VeriDebug, an approach that integrates contrastive representation and guided correction capabilities for automated Verilog debugging. Unlike existing methods, VeriDebug employs an embedding-based technique to accurately retrieve internal information, followed by bug-fixing. VeriDebug unifies Verilog bug detection and correction through a shared parameter space. By simultaneously learning bug patterns and fixes, it streamlines debugging via contrastive embedding and guided correction. Empirical results show the efficacy of VeriDebug in enhancing Verilog debugging. Our VeriDebugLoc, Type model achieves 64.7 accuracy in bug fixing (Acc1), a significant improvement from the existing open-source SOTAs 11.3. This performance not only outperforms open-source alternatives but also exceeds larger closed-source models like GPT-3.5-turbo (36.6), offering a more accurate alternative to conventional debugging methods.