Metraipolis › archive › dc_f06c3137cd0e

Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction — arXiv:2610.21407

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21407
License (as archived)
CC0-1.0
Archived
2026-10-16T10:01:29.477Z
SHA-256 of the archived text
289e8f438f8b9ab80bfb7490bdbc2601070f3388e51aac6b5e094b2b6587f5e7
Stable URL of this page
https://metraipolis.com/documento/dc_f06c3137cd0e

How to cite

Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction — arXiv:2610.21407 — arXiv (en), https://arxiv.org/abs/2610.21407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f06c3137cd0e (Metraipolis archive dc_f06c3137cd0e, sha256 289e8f438f8b9ab80bfb7490bdbc2601070f3388e51aac6b5e094b2b6587f5e7)
BibTeX
@misc{dcf06c3137cd0e,
  title = {Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction — arXiv:2610.21407},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21407},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f06c3137cd0e; sha256 289e8f438f8b9ab80bfb7490bdbc2601070f3388e51aac6b5e094b2b6587f5e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Early stress detection and risk prediction are crucial for timely mental health assessment and support. While large language models have recently shown promise for social media stress prediction, relying on accuracy can obscure false positives. Also, prompt revisions yield inconsistent gains across models and tasks, with unclear links to strategy combinations and instruction changes. By comparing six methods on social media stress and emotion data across two model sizes, we found that GEPA and its extension combining instructions from two prompts (GEPA+merge) improved prediction over initial prompts in several settings. We also identified five prompting strategies associated with development gains. These strategies included directing attention to emotional evidence, distinguishing current from past distress, illustrating indirect cues, requiring emotional context, and guiding label selection. Moreover, we documented four observations across tasks and evaluation settings. In a separate set of searches, binary stress prediction improved early, whereas multilabel emotion prediction initially declined and partly recovered. The other three concerned incorrect or conflicting instructions, gains on small comparison samples that did not hold on full development data, and changes in selected prompts' development and reported test rankings. These findings identify effective prompt evolution methods, strategy combinations associated with gains, and task and evaluation limits, providing guidance for applying prompt evolution methods to social media stress detection.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.21407 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:44:47.651Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).