Xueqing Peng

Multimodal inputs can enhance reasoning in executive decisions, but their indiscriminate use may paradoxically undermine resource allocation effectiveness.

Factorized Hypothesis Search reveals that maintaining multiple interpretations of evidence can dramatically improve taxonomy retrieval accuracy, outperforming conventional methods.

The top-performing systems in multilingual financial question answering are separated by less than one percentage point, showcasing the intense competition and subtlety in model performance.

Systems achieved up to 97.5% accuracy in multilingual financial question answering, revealing the potential for high-performance AI across diverse languages.

Mandate Salience Decay can lead to a 4.4x behavioral gap in financial agents over time, revealing critical vulnerabilities in their long-term deployment.

AuditFlow achieves over 82% accuracy in structured financial audits by leveraging a unique symbolic environment that outperforms traditional methods by nearly 15 points.

Arabic LLMs can speak the language of finance, but they often fail to reason about it, especially when it comes to causality and generation.

LLMs can achieve more consistent and reliable cross-jurisdictional financial reporting by acting as constrained verifiers within a structured, agentic workflow, rather than as free-form generators.

LLMs struggle to balance rational financial decisions with mimicking noisy user behavior, often overfitting to short-term market trends instead of aligning with long-term investment goals.