LLMs for explaining sets of counterfactual examples to final users

Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Jordi Vitrià i Marca

Detalhes bibliográficos
Autor: Fredes Cáceres, Arturo
Tipo de documento: dissertação
Data de publicação:2024
País:España
Recursos:Universidad de Barcelona
Repositório:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/215166
Acesso em linha:https://hdl.handle.net/2445/215166
Access Level:Acceso aberto
Palavra-chave:Aprenentatge automàtic
Tractament del llenguatge natural (Informàtica)
Algorismes computacionals
Treballs de fi de màster
Machine learning
Natural language processing (Computer science)
Computer algorithms
Master's thesis
id ES_450b63262e80da60506044d0bcd3b034
oai_identifier_str oai:diposit.ub.edu:2445/215166
network_acronym_str ES
network_name_str España
repository_id_str
spelling LLMs for explaining sets of counterfactual examples to final usersFredes Cáceres, ArturoAprenentatge automàticTractament del llenguatge natural (Informàtica)Algorismes computacionalsTreballs de fi de màsterMachine learningNatural language processing (Computer science)Computer algorithmsMaster's thesisTreballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Jordi Vitrià i Marca[en] Counterfactual examples have shown to be a promising method for explaining a machine learning model’s decisions, by providing the user with variants of its own data with small shifts to flip the outcome. When a user is presented with a single counterfactual, extracting conclusions from it is straightforward. Yet, this may not reflect the whole scope of possible actions the user can take, and furthermore, the example could be unfeasible. On the other hand, as we increase the number of counterfactuals, drawing conclusions from them becomes difficult for people who are not trained in data analytic thinking. The objective of this work is to evaluate the use of LLMs in producing clear explanations in plain language of these counterfactual examples for the end user. We propose a method to decompose the explanation generation problem into smaller, more manageable tasks to guide the LLM, drawing inspiration from studies on how humans create and communicate explanations. We carry out different experiments using a public dataset and propose a method of closed loop evaluation to assess the coherence of the final explanation with the counterfactuals as well as the quality of the content. Furthermore, an experiment with people is currently being done in order to evaluate the understanding and satisfaction of the users. This work has been submitted for review to the Human-Interpretable Artificial Intelligence (HI-AI) Workshop, held in conjunction with KDD 2024. The submission aims to contribute to the field by presenting findings that enhance the interpretability and understanding of ML systems. The review process is expected to provide insightful feedback that will further refine the methodologies and conclusions discussed in this thesis.Vitrià i Marca, Jordi2024info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2445/215166Màster Oficial - Fonaments de la Ciència de Dadesreponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaIngléscc-by-nc-nd (c) Arturo Fredes Cáceres, 2024codi: GPL (c) Arturo Fredes Cáceres, 2024http://creativecommons.org/licenses/by-nc-nd/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlinfo:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/2151662026-05-27T06:46:51Z
dc.title.none.fl_str_mv LLMs for explaining sets of counterfactual examples to final users
title LLMs for explaining sets of counterfactual examples to final users
spellingShingle LLMs for explaining sets of counterfactual examples to final users
Fredes Cáceres, Arturo
Aprenentatge automàtic
Tractament del llenguatge natural (Informàtica)
Algorismes computacionals
Treballs de fi de màster
Machine learning
Natural language processing (Computer science)
Computer algorithms
Master's thesis
title_short LLMs for explaining sets of counterfactual examples to final users
title_full LLMs for explaining sets of counterfactual examples to final users
title_fullStr LLMs for explaining sets of counterfactual examples to final users
title_full_unstemmed LLMs for explaining sets of counterfactual examples to final users
title_sort LLMs for explaining sets of counterfactual examples to final users
dc.creator.none.fl_str_mv Fredes Cáceres, Arturo
author Fredes Cáceres, Arturo
author_facet Fredes Cáceres, Arturo
author_role author
dc.contributor.none.fl_str_mv Vitrià i Marca, Jordi
dc.subject.none.fl_str_mv Aprenentatge automàtic
Tractament del llenguatge natural (Informàtica)
Algorismes computacionals
Treballs de fi de màster
Machine learning
Natural language processing (Computer science)
Computer algorithms
Master's thesis
topic Aprenentatge automàtic
Tractament del llenguatge natural (Informàtica)
Algorismes computacionals
Treballs de fi de màster
Machine learning
Natural language processing (Computer science)
Computer algorithms
Master's thesis
description Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Jordi Vitrià i Marca
publishDate 2024
dc.date.none.fl_str_mv 2024
dc.type.none.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/215166
url https://hdl.handle.net/2445/215166
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv cc-by-nc-nd (c) Arturo Fredes Cáceres, 2024
codi: GPL (c) Arturo Fredes Cáceres, 2024
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by-nc-nd (c) Arturo Fredes Cáceres, 2024
codi: GPL (c) Arturo Fredes Cáceres, 2024
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
http://www.gnu.org/licenses/gpl-3.0.ca.html
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv Màster Oficial - Fonaments de la Ciència de Dades
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407135234785280
score 15,811543

Registros relacionados