Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespread "blind signing" (approving transactions without understanding them). Through interviews with 16 Web3 users, we find that effective explanations should be structured, risk-aware, and grounded at the token-flow level. Motivated by these findings, we formulate TxSum, a new user-centered NLP task for Ethereum transaction understanding, and construct a dataset of 187 complex Ethereum transactions annotated with transaction-level summaries and token flow-level semantic labels. We further introduce MATEX, a grounded multi-agent framework for high-stakes transaction explanation. It selectively retrieves external knowledge under uncertainty and audits explanations against raw traces to improve token-flow-level factual consistency. MATEX achieves the strongest overall explanation quality, especially on micro-level factuality and intent quality. It improves user comprehension on complex transactions from 52.9% to 76.5% over the strongest baseline and raises malicious-transaction rejection from 36.0% to 88.0%, while maintaining a low false-rejection rate on benign transactions.
@article{arxiv.2512.06933,
title = {TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding},
author = {Zifan Peng and Jingyi Zheng and Yule Liu and Huaiyu Jia and Qiming Ye and Jingyu Liu and Xufeng Yang and Mingchen Li and Qingyuan Gong and Xuechao Wang and Xinlei He},
journal= {arXiv preprint arXiv:2512.06933},
year = {2026}
}