Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation

arXiv:2512.03053v2 Announce Type: replace-cross Abstract: We show for invertible problems that transform data from a source domain (for example, Logic Condition Tables (LCTs)) to a destination domain (for example, Hardware Description Language (HDL) code), an approach of using Large Language Models (LLMs) as a lossless encoder from source to destination followed by as a lossless decoder back to the source, comparable to lossless compression in information theory, can mitigate most of the LLM drawbacks of hallucinations and omissions. Specifically, using LCTs as inputs, we generate the full HDL for a two-dimensional network-on-chip router (13 units, 1500-2000 lines of code) using seven different LLMs, reconstruct the LCTs from the auto-generated HDL, and compare the original and reconstructed LCTs. This approach yields significant productivity improvements, not only confirming correctly generated LLM logic and detecting incorrectly generated LLM logic but also assisting developers in finding design specification errors.

Related

• VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
• HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design
• Syntax Is Easy, Semantics Is Hard: Evaluating LLMs for LTL Translation
• TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
• Decidable By Construction: Design-Time Verification for Trustworthy AI
• Learning Uncertainty from Sequential Internal Dispersion in Large Language Models

Source: arXiv cs.AI | 2026-04-20