arXiv subjects

Bingqiao Luo

Publications and source records attributed to Bingqiao Luo.

8 recordsLinked to original sources

arXiv2025

Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning

While many studies show that more advanced LLMs excel in tasks such as mathematics and coding, we observe that in cryptocurrency trading, stronger LLMs sometimes underperform compared to weaker ones. To investigate this counterintuitive phenomenon, we examine how LLMs reason when making trading decisions. Our findings reveal that (1) stronger LLMs show a preference for factual information over subjectivity; (2) separating the reasoning process into factual and subjective components leads to higher profits. Building on these insights, we propose a multi-agent framework, FS-ReasoningAgent, which enables LLMs to recognize and learn from both factual and subjective reasoning. Extensive experiments demonstrate that this fine-grained reasoning approach enhances LLM trading performance in cryptocurrency markets, yielding profit improvements of 7\% in BTC, 2\% in ETH, and 10\% in SOL. Additionally, an ablation study reveals that relying on subjective news generates higher returns in bull markets, while focusing on factual information yields better results in bear markets. Code is available at https://github.com/Persdre/FS-ReasoningAgent.

cs.MA↗

arXiv2025

LLM-based Human Simulations Have Not Yet Been Reliable

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant discrepancies between their outcomes and authentic human actions. Our investigation begins with a systematic review of LLM-based human simulations in social, economic, policy, and psychological contexts, identifying their common frameworks, recent advances, and persistent limitations. This review reveals that such discrepancies primarily stem from inherent limitations of LLMs and flaws in simulation design, both of which are examined in detail. Building on these insights, we propose a systematic solution framework that emphasizes enriching data foundations, advancing LLM capabilities, and ensuring robust simulation design to enhance reliability. Finally, we introduce a structured algorithm that operationalizes the proposed framework, aiming to guide credible and human-aligned LLM-based simulations. To facilitate further research, we provide a curated list of related literature and resources at https://github.com/Persdre/awesome-llm-human-simulation.

cs.CL↗

arXiv2024

A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading

The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at https://anonymous.4open.science/r/CryptoTrade-Public-92FC/.

q-fin.TR↗

arXiv2024

EX-Graph: A Pioneering Dataset Bridging Ethereum and X

While numerous public blockchain datasets are available, their utility is constrained by an exclusive focus on blockchain data. This constraint limits the incorporation of relevant social network data into blockchain analysis, thereby diminishing the breadth and depth of insight that can be derived. To address the above limitation, we introduce EX-Graph, a novel dataset that authentically links Ethereum and X, marking the first and largest dataset of its kind. EX-Graph combines Ethereum transaction records (2 million nodes and 30 million edges) and X following data (1 million nodes and 3 million edges), bonding 30,667 Ethereum addresses with verified X accounts sourced from OpenSea. Detailed statistical analysis on EX-Graph highlights the structural differences between X-matched and non-X-matched Ethereum addresses. Extensive experiments, including Ethereum link prediction, wash-trading Ethereum addresses detection, and X-Ethereum matching link prediction, emphasize the significant role of X data in enhancing Ethereum analysis. EX-Graph is available at \url{https://exgraph.deno.dev/}.

cs.SI↗

arXiv2024

AI-powered Fraud Detection in Decentralized Finance: A Project Life Cycle Perspective

In recent years, blockchain technology has introduced decentralized finance (DeFi) as an alternative to traditional financial systems. DeFi aims to create a transparent and efficient financial ecosystem using smart contracts and emerging decentralized applications. However, the growing popularity of DeFi has made it a target for fraudulent activities, resulting in losses of billions of dollars due to various types of frauds. To address these issues, researchers have explored the potential of artificial intelligence (AI) approaches to detect such fraudulent activities. Yet, there is a lack of a systematic survey to organize and summarize those existing works and to identify the future research opportunities. In this survey, we provide a systematic taxonomy of various frauds in the DeFi ecosystem, categorized by the different stages of a DeFi project's life cycle: project development, introduction, growth, maturity, and decline. This taxonomy is based on our finding: many frauds have strong correlations in the stage of the DeFi project. According to the taxonomy, we review existing AI-powered detection methods, including statistical modeling, natural language processing and other machine learning techniques, etc. We find that fraud detection in different stages employs distinct types of methods and observe the commendable performance of tree-based and graph-related models in tackling fraud detection tasks. By analyzing the challenges and trends, we present the findings to provide proactive suggestion and guide future research in DeFi fraud detection. We believe that this survey is able to support researchers, practitioners, and regulators in establishing a secure and trustworthy DeFi ecosystem.

cs.CE↗

arXiv2024

When Crypto Economics Meet Graph Analytics and Learning

Utilizing graph analytics and learning has proven to be an effective method for exploring aspects of crypto economics such as network effects, decentralization, tokenomics, and fraud detection. However, the majority of existing research predominantly focuses on leading cryptocurrencies, namely Bitcoin (BTC) and Ethereum (ETH), overlooking the vast diversity among the more than 10,000 cryptocurrency projects. This oversight may result in skewed insights. In our paper, we aim to broaden the scope of investigation to encompass the entire spectrum of cryptocurrencies, examining various coins across their entire life cycles. Furthermore, we intend to pioneer advanced methodologies, including graph transfer learning and the innovative concept of "graph of graphs". By extending our research beyond the confines of BTC and ETH, our goal is to enhance the depth of our understanding of crypto economics and to advance the development of more intricate graph-based techniques.

cs.CE↗

arXiv2023

BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection

As various forms of fraud proliferate on Ethereum, it is imperative to safeguard against these malicious activities to protect susceptible users from being victimized. While current studies solely rely on graph-based fraud detection approaches, it is argued that they may not be well-suited for dealing with highly repetitive, skew-distributed and heterogeneous Ethereum transactions. To address these challenges, we propose BERT4ETH, a universal pre-trained Transformer encoder that serves as an account representation extractor for detecting various fraud behaviors on Ethereum. BERT4ETH features the superior modeling capability of Transformer to capture the dynamic sequential patterns inherent in Ethereum transactions, and addresses the challenges of pre-training a BERT model for Ethereum with three practical and effective strategies, namely repetitiveness reduction, skew alleviation and heterogeneity modeling. Our empirical evaluation demonstrates that BERT4ETH outperforms state-of-the-art methods with significant enhancements in terms of the phishing account detection and de-anonymization tasks. The code for BERT4ETH is available at: https://github.com/git-disl/BERT4ETH.

cs.CR↗

arXiv2023

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

Numerous studies have been conducted to investigate the properties of large-scale temporal graphs. Despite the ubiquity of these graphs in real-world scenarios, it's usually impractical for us to obtain the whole real-time graphs due to privacy concerns and technical limitations. In this paper, we introduce the concept of {\it Live Graph Lab} for temporal graphs, which enables open, dynamic and real transaction graphs from blockchains. Among them, Non-fungible tokens (NFTs) have become one of the most prominent parts of blockchain over the past several years. With more than \$40 billion market capitalization, this decentralized ecosystem produces massive, anonymous and real transaction activities, which naturally forms a complicated transaction network. However, there is limited understanding about the characteristics of this emerging NFT ecosystem from a temporal graph analysis perspective. To mitigate this gap, we instantiate a live graph with NFT transaction network and investigate its dynamics to provide new observations and insights. Specifically, through downloading and parsing the NFT transaction activities, we obtain a temporal graph with more than 4.5 million nodes and 124 million edges. Then, a series of measurements are presented to understand the properties of the NFT ecosystem. Through comparisons with social, citation, and web networks, our analyses give intriguing findings and point out potential directions for future exploration. Finally, we also study machine learning models in this live graph to enrich the current datasets and provide new opportunities for the graph community. The source codes and dataset are available at https://livegraphlab.github.io.

cs.AI↗