Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoon, Yejun, Jung, Jaeyoon, Yoon, Seunghyun, Park, Kunwoo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916844540002304
author Yoon, Yejun
Jung, Jaeyoon
Yoon, Seunghyun
Park, Kunwoo
author_facet Yoon, Yejun
Jung, Jaeyoon
Yoon, Seunghyun
Park, Kunwoo
contents This paper presents HerO 2, Team HUMANE's system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year's challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification
Yoon, Yejun
Jung, Jaeyoon
Yoon, Seunghyun
Park, Kunwoo
Computation and Language
This paper presents HerO 2, Team HUMANE's system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year's challenge. It improves evidence quality through document summarization and answer reformulation, optimizes veracity prediction via post-training quantization under computational constraints, and enhances overall system performance by integrating updated language model (LM) backbones. HerO 2 ranked second on the leaderboard while achieving the shortest runtime among the top three systems, demonstrating both high efficiency and strong potential for real-world fact verification. The code is available at https://github.com/ssu-humane/HerO2.
title Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification
topic Computation and Language
url https://arxiv.org/abs/2507.11004