Updated 2/22/2026
The STEP-LLM framework, utilized for generating Computer-Aided Design (CAD) STEP files (ISO 10303) from natural language, exhibits a safety alignment vulnerability during the fine-tuning of base Large Language Models (specifically Llama-3.2-3B-Instruct and Qwen-2.5-3B). The training pipeline employs Depth-First Search (DFS) reserialization and Reinforcement Learning (RL) with Scaled Chamfer Distance rewards to optimize for geometric fidelity and syntactic validity of Boundary Representation…
STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models
Affects: GPT-4o, Llama 3.2 3B, Qwen 2.5 3B
Source: arXiv