AI RESEARCH
To Write or to Automate Linguistic Prompts, That Is the Question
arXiv CS.CL
•
ArXi:2603.25169v1 Announce Type: new LLM performance is highly sensitive to prompt design, yet whether automatic prompt optimization can replace expert prompt engineering in linguistic tasks remains unexplored. We present the first systematic comparison of hand-crafted zero-shot expert prompts, base DSPy signatures, and GEPA-optimized DSPy signatures across translation, terminology insertion, and language quality assessment, evaluating five model configurations. Results are task-dependent.