{"ID":2894252,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.11004","arxiv_id":"2507.11004","title":"Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification","abstract":"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.","short_abstract":"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 veracit...","url_abs":"https://arxiv.org/abs/2507.11004","url_pdf":"https://arxiv.org/pdf/2507.11004v1","authors":"[\"Yejun Yoon\",\"Jaeyoon Jung\",\"Seunghyun Yoon\",\"Kunwoo Park\"]","published":"2025-07-15T05:42:50Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":612104,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2894252,"paper_url":"https://arxiv.org/abs/2507.11004","paper_title":"Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification","repo_url":"https://github.com/ssu-humane/HerO2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}