Metraipolis › archive › dc_525b474bd5ea
Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment — arXiv:2609.07766
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07766
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:45:46.336Z
- SHA-256 of the archived text
8a0da8d739ca11e6162f02ce1c82c74615db29a46848511c29be0724da12da5c- Stable URL of this page
https://metraipolis.com/documento/dc_525b474bd5ea
How to cite
Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment — arXiv:2609.07766 — arXiv (en), https://arxiv.org/abs/2609.07766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_525b474bd5ea (Metraipolis archive dc_525b474bd5ea, sha256 8a0da8d739ca11e6162f02ce1c82c74615db29a46848511c29be0724da12da5c)
BibTeX
@misc{dc525b474bd5ea,
title = {Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment — arXiv:2609.07766},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07766},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_525b474bd5ea; sha256 8a0da8d739ca11e6162f02ce1c82c74615db29a46848511c29be0724da12da5c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Assessing suicide risk from social media text is a small-data, high-stakes setting requiring not only severity prediction but also supporting evidence and clinically relevant risk and protective factors. Yet common NLP techniques, including model scaling, synthetic data, loss reweighting, ensembling, and threshold tuning, are often applied without testing whether their gains hold up under severe class imbalance, coupled outputs, and limited author-level data. We study 1,635 clinician-annotated posts and audit 31 pre-specified techniques from 7 methodological families through roughly 300 controlled experiments on author-disjoint partitions. We found no prior audit of this playbook in this regime. The findings guide a task-grounded system for three outputs: 4-level suicide risk, evidence spans, and 24 clinical risk and protective factors. Only 5 of 31 comparisons produced reliable gains. We reformulate factor prediction as entailment between each post and its codebook definitions, using an architecturally diverse ensemble with class-balanced training and score rescaling. Risk predictions condition a 7-model evidence tagger ensemble; evidence restricts symbolic risk rules; and a difficult risk class is routed separately. The factor predictor remains independent because risk evidence provides no additional factor signal. We also correct a mismatch between validation scores used for threshold fitting and test-time ensemble scores through deployment-consistent calibration, yielding the largest improvement to the factor system. The final system achieves 0.8203 for risk, 0.7953 for evidence, and 0.7045 macro-F1 for factors, with a 0.7781 composite, ranking third among 53 teams. We call the underlying principle task-conditioned technique selection: retain techniques only when task-specific knowledge, structure, or empirical evidence justifies them. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.07766 — 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 2026-10-16T12:30:25.140Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).