Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Recolector de Ciencia Abierta, RECOLECTA
Bachelor thesis . 2024
License: CC BY NC ND
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
UCrea
Bachelor thesis . 2024
License: CC BY NC ND
Data sources: UCrea
versions View all 2 versions
addClaim

Entrevistador virtual utilizando técnicas RAG en LLMs

Virtual interviewer using RAG techniques in LLMs
Authors: Elizalde Roldán, Raúl;

Entrevistador virtual utilizando técnicas RAG en LLMs

Abstract

En un mundo cada vez más digitalizado y competitivo parece no solo aconsejable sino necesario optimizar las prácticas de selección de personal con las herramientas tecnológicas adecuadas. En concreto, incorporar técnicas de Inteligencia Artificial al ámbito de las entrevistas laborales presenta a la vez un desafío y la oportunidad de automatizar y mejorar significativamente el proceso de selección de personal. El objetivo del proyecto es obtener un Sistema de Aprendizaje Automático (SAA) para entrevistas laborales utilizando un enfoque basado en modelos de lenguaje de gran tamaño (LLMs o Large Language Models). Durante el desarrollo se han elegido diferentes modelos a los que se le aplican técnicas RAG. Para aplicar RAG, se ha seleccionado un corpus de entrenamiento relacionado con las entrevistas laborales. Finalmente, se realiza un análisis y evaluación de las pruebas realizadas. Entre las herramientas y tecnologías a utilizar se incluyen Python (incorporando Pytorch) y Google Colab y, como modelos LLM, Llama2 o Mistral entre otros. El TFG se desarrolla en el programa observatorio de la empresa HP con sede en León bajo la supervisión de Sergio Martínez Prieto como tutor de la entidad y de Inés González Rodríguez como tutora académica.

Grado en Ingeniería Informática

Country
Spain
Related Organizations
Keywords

LLM, Generative AI, IA generativa, RAG, NLP

  • BIP!
    Impact byBIP!
    citations
    The total number of citations received by all articles of the researcher of interest.
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
The total number of citations received by all articles of the researcher of interest.
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average