TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding
cs.CE, cs.CL, cs.HC
Submitted: 2025-12-07
Updated: 2026-08-31
Comments: EMNLP 2026
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: 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
Terminology
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 domain-grounded NLP task for DeFi transaction explanation, and construct a dataset of 187 complex Ethereum transactions with 2,375 token-flow annotations and transaction-level summaries. 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.
Sources
- TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum
- Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining
- GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts
Related papers
- Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor
- Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval
- Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad
- Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness
- RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
- Wildfire Suppression: Complexity, Models, and Instances