Metraipolis › archive › dc_a4df44dae17d
Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use — arXiv:2610.32193
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32193
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:47:45.104Z
- SHA-256 of the archived text
5c5d937ed19a15140bb2615657c1aa9db07c0eada3fd50c8bd8700061f5cec6c- Stable URL of this page
https://metraipolis.com/documento/dc_a4df44dae17d
How to cite
Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use — arXiv:2610.32193 — arXiv (en), https://arxiv.org/abs/2610.32193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4df44dae17d (Metraipolis archive dc_a4df44dae17d, sha256 5c5d937ed19a15140bb2615657c1aa9db07c0eada3fd50c8bd8700061f5cec6c)
BibTeX
@misc{dca4df44dae17d,
title = {Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use — arXiv:2610.32193},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32193},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4df44dae17d; sha256 5c5d937ed19a15140bb2615657c1aa9db07c0eada3fd50c8bd8700061f5cec6c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Users often exhibit changes in interaction behavior before explicitly seeking assistance, enabling systems to anticipate future assistance use. This is especially important in high-stakes environments, where delayed assistance can have operational, financial, or safety consequences. However, conventional Large Language Models (LLMs) are often unsuitable for continuous on-device behavioral prediction because of their computational and memory demands. Behavioral patterns are also highly individual and device-specific, motivating local processing that preserves privacy and data sovereignty. Small Language Models (SLMs) offer a promising alternative, but their ability to reason reliably over low-level sequential interaction events remains underexplored. This study introduces Evidence-Grounded Local Behavioral Prediction (ELBP), a four-layer architecture combining deterministic interaction processing, dual-view behavioral representation, SLM-based prediction, and evidence verification with abstention. Three instruction-tuned models of 3B parameters or fewer were evaluated using raw, structured, dual-view, and complete ELBP configurations. The best-performing model, Qwen2.5-3B with ELBP, achieved a full-set F1-score of 0.80 and PR-AUC of 0.84, representing a 15.9\% relative improvement over raw-event prompting and 17.6\% over XGBoost, while full-set ECE decreased by 43.2\% relative to raw-event prompting. With evidence verification and abstention, selective F1 increased to 0.84 at 91\% coverage and evidence support reached 96\%. These results show that structured behavioral representation and evidence-verified selective prediction can improve the reliability of behavioral forecasting in SLMs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.32193 — 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 2026-10-26T19:45:33.290Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).