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

2025/07/15 by Yoon, Yejun, Jung, Jaeyoon, Yoon, Seunghyun +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2507.11004

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.

Citations

• Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking
• The Automated Verification of Textual Claims (AVeriTeC) Shared Task
• HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims
• Towards General Text Embeddings with Multi-stage Contrastive Learning
• AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Related

• HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims
• (Fact) Check Your Bias
• AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task
• Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval
• GPTs at Factify 2022: Prompt Aided Fact-Verification