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

arXiv: https://arxiv.org/abs/2512.06933 · HTML: https://mlsanity.com/paper/2512.06933/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 66 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Securify: Practical Security Analysis of Smart Contracts](https://mlsanity.com/paper/1806.01143/) (2018)
- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [HedgeAgents: A Balanced-aware Multi-agent Financial Trading System](https://mlsanity.com/paper/2502.13165/) (2025)
- [Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search](https://mlsanity.com/paper/2502.04951/) (2025)
- [XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning](https://mlsanity.com/paper/2508.15861/) (2025)
- [On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing](https://mlsanity.com/paper/2412.17242/) (2024)
- [SCALM: Detecting Bad Practices in Smart Contracts Through LLMs](https://mlsanity.com/paper/2502.04347/) (2025)
- [TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors](https://mlsanity.com/paper/2503.08708/) (2025)
- [Auditing Data Membership in Reinforcement Learning With Verifiable Rewards](https://mlsanity.com/paper/2511.14045/) (2025)
- [GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts](https://mlsanity.com/paper/2507.15761/) (2025)
- [Know Your Intent: An Autonomous Multi-Perspective LLM Agent Framework for DeFi User Transaction Intent Mining](https://mlsanity.com/paper/2511.15456/) (2025)
- [PonziLens+: Visualizing Bytecode Actions for Smart Ponzi Scheme Identification](https://mlsanity.com/paper/2412.18470/) (2024)
- [Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study](https://mlsanity.com/paper/2501.18158/) (2025)
- [Cross-Chain Options: A Bridgeless, Universal, and Efficient Approach](https://mlsanity.com/paper/2410.15724/) (2024)
- [Stealing Trust: Unraveling Blind Message Attacks in Web3 Authentication](https://mlsanity.com/paper/2406.00523/) (2024)
- [I Experienced More than 10 DeFi Scams: On DeFi Users' Perception of Security Breaches and Countermeasures](https://mlsanity.com/paper/2406.15709/) (2024)
- [PrettiSmart: Visual Interpretation of Smart Contracts via Simulation](https://mlsanity.com/paper/2412.18484/) (2024)
- [TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum](https://mlsanity.com/paper/2509.03037/) (2025)

## Built on by (most cited first, 1 of 1)

- [What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media](https://mlsanity.com/paper/2606.06784/) (2026)

## Abstract (arXiv)

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.