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

arXiv: https://arxiv.org/abs/2507.11004 · HTML: https://mlsanity.com/paper/2507.11004/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [The Automated Verification of Textual Claims (AVeriTeC) Shared Task](https://mlsanity.com/paper/2410.23850/) (2024)
- [Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking](https://mlsanity.com/paper/2411.05375/) (2024)
- [HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims](https://mlsanity.com/paper/2410.12377/) (2024)

## Built on by (most cited first, 4 of 4)

- [One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking](https://mlsanity.com/paper/2601.11293/) (2026)
- [VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration](https://mlsanity.com/paper/2602.04587/) (2026)
- [Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessity](https://mlsanity.com/paper/2604.04692/) (2026)
- [Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation](https://mlsanity.com/paper/2609.08943/) (2026)

## Abstract (arXiv)

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.