To Write or to Automate Linguistic Prompts, That Is the Question

Marina Sánchez-Torrón, Daria Akselrod, Jason Rauchwerk


Abstract
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. In terminology insertion, optimized and manual prompts produce mostly statistically indistinguishable quality. In translation, each approach wins on different models. In LQA, expert prompts achieve stronger error detection while optimization improves characterization. Across all tasks, GEPA elevates minimal DSPy signatures, and the majority of expert–optimized comparisons show no statistically significant difference. We note that the comparison is asymmetric: GEPA optimization searches programmatically over gold-standard splits, whereas expert prompts require in principle no labeled data, relying instead on domain expertise and iterative refinement.
Anthology ID:
2026.eamt-1.8
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
85–95
Language:
URL:
https://aclanthology.org/2026.eamt-1.8/
DOI:
Bibkey:
Cite (ACL):
Marina Sánchez-Torrón, Daria Akselrod, and Jason Rauchwerk. 2026. To Write or to Automate Linguistic Prompts, That Is the Question. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 85–95, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
To Write or to Automate Linguistic Prompts, That Is the Question (Sánchez-Torrón et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.8.pdf