Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification
This incremental improvement addresses efficient fact verification for real-world applications, building on prior work.
The paper tackled fact verification by enhancing the HerO system with document summarization, answer reformulation, and post-training quantization, resulting in a second-place ranking on the AVeriTeC 2025 leaderboard and the shortest runtime among top systems.
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.