Yixuan Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yixuan Lu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Chen Chen
Vanderbilt University, Nashville, USA
2 shared publications - Hejing Chen
Walsh College, Troy, USA
2 shared publications - Ruibo Wu
University of California, San Diego, La Jolla, USA
2 shared publications - Ao Zhu
University of Pennsylvania, Philadelphia, USA
1 shared publication - Hanrui Feng
University of Chicago, Chicago, USA
1 shared publication - Jinyan Lyu
Columbia University, New York, USA
1 shared publication
Latest Publications
- Open Access
- 29 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 292-297
Multi-Agent Framework for Audit Risk Assessment with Explicit Uncertainty and Evidence Conflict Modeling
- 29 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 292-297
Open AccessMulti-Agent Framework for Audit Risk Assessment with Explicit Uncertainty and Evidence Conflict Modeling
- Open Access
- 6 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 368-376
Anomaly Ranking for Enterprise Finance Using Latent Structural Deviations and Reconstruction Consistency
- 6 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 368-376
Open AccessAnomaly Ranking for Enterprise Finance Using Latent Structural Deviations and Reconstruction Consistency
- Top Cited PapersOpen Access
- 9 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 566-573
Causal-LLM: A Hybrid Framework for Automated Budgetary Variance Diagnosis and Reasoning
Traditional Enterprise Resource Planning (ERP) systems excel at quantifying budgetary variances but fail to identify their root causes, leaving financial analysts with time-consuming manual investigation. We present Causal-LLM, a hybrid framework that integrates causal discovery algorithms with Large Language Models (LLMs) to automate root cause diagnosis in budgetary variance analysis. Our approach combines constraint-based causal inference to construct financial causal graphs with LLM-powered contextual reasoning to generate human-interpretable explanations. By leveraging a domain-specific Financial Causal Knowledge Graph, Causal-LLM bridges the gap between statistical correlation and genuine causation. Experimental evaluation on 240 labeled variance cases from a real-world enterprise (24 months of data) demonstrates that our framework achieves 0.87 top-1 accuracy in root cause identification (95% CI: [0.82, 0.91]), outperforming traditional statistical methods (0.68), pure LLM approaches (0.76), and standalone causal methods (0.72). The system generates actionable insights with 0.92 explainability scores (inter-rater agreement ICC=0.84), reducing investigation time from an estimated 2–4 hours (mean: 3.2 hours, based on internal workflow estimates from five senior analysts) to under 10 seconds per case. Results are demonstrated on one manufacturing enterprise; generalization to other industries requires domain-specific ontology adaptation.
- 9 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 566-573
Top Cited PapersOpen AccessCausal-LLM: A Hybrid Framework for Automated Budgetary Variance Diagnosis and Reasoning
Traditional Enterprise Resource Planning (ERP) systems excel at quantifying budgetary variances but fail to identify their root causes, leaving financial analysts with time-consuming manual investigation. We present Causal-LLM, a hybrid framework that integrates causal discovery algorithms with Large Language Models (LLMs) to automate root cause diagnosis in budgetary variance analysis. Our approach combines constraint-based causal inference to construct financial causal graphs with LLM-powered contextual reasoning to generate human-interpretable explanations. By leveraging a domain-specific Financial Causal Knowledge Graph, Causal-LLM bridges the gap between statistical correlation and genuine causation. Experimental evaluation on 240 labeled variance cases from a real-world enterprise (24 months of data) demonstrates that our framework achieves 0.87 top-1 accuracy in root cause identification (95% CI: [0.82, 0.91]), outperforming traditional statistical methods (0.68), pure LLM approaches (0.76), and standalone causal methods (0.72). The system generates actionable insights with 0.92 explainability scores (inter-rater agreement ICC=0.84), reducing investigation time from an estimated 2–4 hours (mean: 3.2 hours, based on internal workflow estimates from five senior analysts) to under 10 seconds per case. Results are demonstrated on one manufacturing enterprise; generalization to other industries requires domain-specific ontology adaptation.
- Open Access
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 822-826
Few-Shot Financial Fraud Detection Using Meta-Learning and Large Language Models
- 26 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 822-826
Open AccessFew-Shot Financial Fraud Detection Using Meta-Learning and Large Language Models