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

TL;DR

HerO 2, an improved fact verification system, enhances evidence quality, optimizes veracity prediction, and achieves high efficiency, ranking second with the shortest runtime at AVeriTeC 2025.

Contribution

This work introduces HerO 2, a novel system that advances fact verification by integrating document summarization, answer reformulation, and model optimization techniques.

Findings

Ranked second on the leaderboard.

Achieved the shortest runtime among top systems.

Demonstrated high efficiency and potential for real-world use.

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.