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

TL;DR

This paper introduces TxSum, a new NLP task and dataset for understanding Ethereum transactions at a micro-level, and presents MATEX, a framework that improves explanation quality and user comprehension of complex transactions.

Contribution

The paper formulates a novel user-centered NLP task for Ethereum transaction understanding, creates a detailed dataset, and develops MATEX, a grounded multi-agent framework for high-stakes transaction explanations.

Findings

MATEX significantly improves user comprehension from 52.9% to 76.5%.

It increases malicious transaction rejection from 36.0% to 88.0%.

The approach maintains low false-rejection rates on benign transactions.

Abstract

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.