Loki: An Open-Source Tool for Fact Verification

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Haonan, Han, Xudong, Wang, Hao, Wang, Yuxia, Wang, Minghan, Xing, Rui, Geng, Yilin, Zhai, Zenan, Nakov, Preslav, Baldwin, Timothy
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929524510294016
author Li, Haonan
Han, Xudong
Wang, Hao
Wang, Yuxia
Wang, Minghan
Xing, Rui
Geng, Yilin
Zhai, Zenan
Nakov, Preslav
Baldwin, Timothy
author_facet Li, Haonan
Han, Xudong
Wang, Hao
Wang, Yuxia
Wang, Minghan
Xing, Rui
Geng, Yilin
Zhai, Zenan
Nakov, Preslav
Baldwin, Timothy
contents We introduce Loki, an open-source tool designed to address the growing problem of misinformation. Loki adopts a human-centered approach, striking a balance between the quality of fact-checking and the cost of human involvement. It decomposes the fact-checking task into a five-step pipeline: breaking down long texts into individual claims, assessing their check-worthiness, generating queries, retrieving evidence, and verifying the claims. Instead of fully automating the claim verification process, Loki provides essential information at each step to assist human judgment, especially for general users such as journalists and content moderators. Moreover, it has been optimized for latency, robustness, and cost efficiency at a commercially usable level. Loki is released under an MIT license and is available on GitHub. We also provide a video presenting the system and its capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01794
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Loki: An Open-Source Tool for Fact Verification
Li, Haonan
Han, Xudong
Wang, Hao
Wang, Yuxia
Wang, Minghan
Xing, Rui
Geng, Yilin
Zhai, Zenan
Nakov, Preslav
Baldwin, Timothy
Computation and Language
We introduce Loki, an open-source tool designed to address the growing problem of misinformation. Loki adopts a human-centered approach, striking a balance between the quality of fact-checking and the cost of human involvement. It decomposes the fact-checking task into a five-step pipeline: breaking down long texts into individual claims, assessing their check-worthiness, generating queries, retrieving evidence, and verifying the claims. Instead of fully automating the claim verification process, Loki provides essential information at each step to assist human judgment, especially for general users such as journalists and content moderators. Moreover, it has been optimized for latency, robustness, and cost efficiency at a commercially usable level. Loki is released under an MIT license and is available on GitHub. We also provide a video presenting the system and its capabilities.
title Loki: An Open-Source Tool for Fact Verification
topic Computation and Language
url https://arxiv.org/abs/2410.01794