TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Peng, Zifan, Zheng, Jingyi, Liu, Yule, Jia, Huaiyu, Ye, Qiming, Liu, Jingyu, Yang, Xufeng, Li, Mingchen, Gong, Qingyuan, Wang, Xuechao, He, Xinlei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912971746181120
author Peng, Zifan
Zheng, Jingyi
Liu, Yule
Jia, Huaiyu
Ye, Qiming
Liu, Jingyu
Yang, Xufeng
Li, Mingchen
Gong, Qingyuan
Wang, Xuechao
He, Xinlei
author_facet Peng, Zifan
Zheng, Jingyi
Liu, Yule
Jia, Huaiyu
Ye, Qiming
Liu, Jingyu
Yang, Xufeng
Li, Mingchen
Gong, Qingyuan
Wang, Xuechao
He, Xinlei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06933
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding
Peng, Zifan
Zheng, Jingyi
Liu, Yule
Jia, Huaiyu
Ye, Qiming
Liu, Jingyu
Yang, Xufeng
Li, Mingchen
Gong, Qingyuan
Wang, Xuechao
He, Xinlei
Computational Engineering, Finance, and Science
Computation and Language
Human-Computer Interaction
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.
title TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding
topic Computational Engineering, Finance, and Science
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2512.06933