Parental Cooperation from Swiss Child Protection Reports: Reasoning Language Models Outperform Retrieval-Augmented Generation
Research on Social Work Practice · 09.07.2026
DOI: 10.1177/10497315261446932 ↗Kurz gefasst
Fachartikel in der Zeitschrift Research on Social Work Practice, online erschienen am 09.07.2026. Verfasst von Dragan Stoll und 5 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Purpose
Assessing parental cooperation during child protection services (CPSs) interventions raises distinctive analytical challenges due to ambiguous, conflicting information. We compared reasoning language models (RLMs) to retrieval-augmented generation (RAG) in classifying parental cooperation from Swiss CPS reports.
Methods
RLMs of three parameter sizes (255B, 32B, 4B) were benchmarked against a RAG-based approach using a consensus dataset of 100 reports independently classified by two expert human reviewers.
Results
The largest RLM achieved the highest accuracy (89%), a nine-point improvement over RAG (80%), approaching expert inter-rater reliability (κ = 0.76). Accuracy was higher for mothers (93%) than fathers (85%), mirrored by expert reviewers. Applied to the full corpus, 31% of cases ( n = 3,900) had at least one parent with documented noncooperation.
Discussion
RLMs outperformed RAG and approached expert reliability in classifying parental cooperation. Gender differences likely reflect documentation biases rather than model limitations, corroborating the stronger professional focus on mothers.
Zitieren
APA
Stoll, D., Perron, B. E., Qi, Z., Steinmann, S., Eicher, N. F., & Jud, A. (2026). Parental Cooperation from Swiss Child Protection Reports: Reasoning Language Models Outperform Retrieval-Augmented Generation. Research on Social Work Practice. https://doi.org/10.1177/10497315261446932
Vancouver
Stoll D, Perron BE, Qi Z, Steinmann S, Eicher NF, Jud A. Parental Cooperation from Swiss Child Protection Reports: Reasoning Language Models Outperform Retrieval-Augmented Generation. Research on Social Work Practice. 2026. doi:10.1177/10497315261446932
BibTeX
@article{Stoll2026,
author = {Stoll, Dragan and Perron, Brian E. and Qi, Zia and Steinmann, Selina and Eicher, Nicole F. and Jud, Andreas},
title = {Parental Cooperation from Swiss Child Protection Reports: Reasoning Language Models Outperform Retrieval-Augmented Generation},
journal = {Research on Social Work Practice},
year = {2026},
doi = {10.1177/10497315261446932}
}
EUVIMED