@misc{10481/91737,
year = {2024},
month = {3},
url = {https://hdl.handle.net/10481/91737},
abstract = {Generative language models have changed the way we interact with computers using natural
language. With the release of increasingly advanced GPT models, systems are able to correctly
respond to questions in various domains. However, they still have important limitations, such as
hallucinations, lack of substance in answers, inability to justify responses, or showing high
confidence with fabricated content. In digital mental health, every decision must be traceable
and based on scientific evidence and these shortcomings are hindering the integration of LLMs
into clinical practice. In this paper, we provide a novel automated method to develop evidencebased
question answering systems. Powerful state-of-the-art generalist language models are
used and forced to employ only contents in validated clinical guidelines, tracking the source of
the evidence for each generated response. This way, the system is able to protect users from
hallucinatory responses. As a proof of concept, we present the results obtained building
question-answering systems circumscribed to the clinical practice guidelines of the Spanish
National Health System about the management of depression and attention deficit
hyperactivity disorder. The coherence, veracity, and evidence supporting the responses have
been evaluated by human experts obtaining high reliability, clarity, completeness, and
traceability of evidence results.},
organization = {‘CONVERSA: Effective and efficient resources and models for transformative conversational AI in Spanish and co-official languages’ project with reference (Agencia Estatal de Investigación) TED2021- 132470B-I00, funded by MCIN/AEI/10.13039/501100011033 and by the European Union ‘NextGenerationEU/PRTR’},
organization = {European Union’s Horizon 2020 research and innovation programme under grant agreement No 823907 (MENHIR, https://menhir-project.eu)},
publisher = {Taylor & Francis Group},
keywords = {Question-answering},
keywords = {Generative language model},
keywords = {Large language model},
title = {Incorporating evidence into mental health Q&A: a novel method to use generative language models for validated clinical content extraction},
doi = {10.1080/0144929X.2024.2321959},
author = {Kharitonova, Ksenia and Pérez Fernández, David and Gutiérrez Hernando, Javier and Gutiérrez Fandiño, Asier and Callejas Carrión, Zoraida and Griol Barres, David},
}