Metraipolis › archive › dc_719c28cc439c
Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation — arXiv:2610.09209
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09209
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:10:41.370Z
- SHA-256 of the archived text
2812df6be9d72929961839e3bbb5fec4ccf67c1e12adea173329922aed74fa3e- Stable URL of this page
https://metraipolis.com/documento/dc_719c28cc439c
How to cite
Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation — arXiv:2610.09209 — arXiv (en), https://arxiv.org/abs/2610.09209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_719c28cc439c (Metraipolis archive dc_719c28cc439c, sha256 2812df6be9d72929961839e3bbb5fec4ccf67c1e12adea173329922aed74fa3e)
BibTeX
@misc{dc719c28cc439c,
title = {Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation — arXiv:2610.09209},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09209},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_719c28cc439c; sha256 2812df6be9d72929961839e3bbb5fec4ccf67c1e12adea173329922aed74fa3e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and readiness for change. Although large language models (LLMs) can generate fluent text, they often fail to produce cognitively coherent and clinically realistic patient behavior, especially under ethical and data-scarce clinical settings. Moreover, deploying frontier-scale LLMs in healthcare applications presents practical challenges including high computational cost, latency, privacy concerns, and limited deployability in resource-constrained environments, motivating the need for cognitively aligned small language models (SLMs). We propose a cognitively grounded framework for SUD patient dialogue generation that explicitly models and aligns latent cognitive components with patient histories and counselor questions. Our pipeline consists of two stages: cognitive component detection and cognitive component-aligned dialogue generation. To enable effective learning with smaller models, we combine knowledge distillation from high-capacity teacher models, preference optimization from human-annotations, and attention-guided reward shaping. Extensive evaluations using automatic scores like BERTScore, ROUGE, METEOR and BLEU, and LLM-as-judge hit-metrics against both human and teacher-model references show that cognitively informed fine-tuning substantially improves cognitive realization and alignment over a generic instruction-tuned baselines and mental health domain specific SLMs, with particularly strong gains for open-ended cognitive components. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.09209 — 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 2026-10-08T10:14:06.058Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).