Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Karamolegkou, Antonia, Hansen, Sandrine Schiller, Christopoulou, Ariadni, Stamatiou, Filippos, Lauscher, Anne, Søgaard, Anders
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912116271742976
author Karamolegkou, Antonia
Hansen, Sandrine Schiller
Christopoulou, Ariadni
Stamatiou, Filippos
Lauscher, Anne
Søgaard, Anders
author_facet Karamolegkou, Antonia
Hansen, Sandrine Schiller
Christopoulou, Ariadni
Stamatiou, Filippos
Lauscher, Anne
Søgaard, Anders
contents What ethical concerns, if any, do LLM researchers have? We introduce EthiCon, a corpus of 1,580 ethical concern statements extracted from scientific papers published in the ACL Anthology. We extract ethical concern keywords from the statements and show promising results in automating the concern identification process. Through a survey, we compare the ethical concerns of the corpus to the concerns listed by the general public and professionals in the field. Finally, we compare our retrieved ethical concerns with existing taxonomies pointing to gaps and future research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements
Karamolegkou, Antonia
Hansen, Sandrine Schiller
Christopoulou, Ariadni
Stamatiou, Filippos
Lauscher, Anne
Søgaard, Anders
Computation and Language
Artificial Intelligence
Computers and Society
What ethical concerns, if any, do LLM researchers have? We introduce EthiCon, a corpus of 1,580 ethical concern statements extracted from scientific papers published in the ACL Anthology. We extract ethical concern keywords from the statements and show promising results in automating the concern identification process. Through a survey, we compare the ethical concerns of the corpus to the concerns listed by the general public and professionals in the field. Finally, we compare our retrieved ethical concerns with existing taxonomies pointing to gaps and future research directions.
title Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements
topic Computation and Language
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2411.07845