Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify re...
Hoyoung Lee, Suyeol Yun, J. Haverty et al.· 0 citations
Across financial filings and earnings-call transcripts, it is found that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions, suggesting that financial compression should be evaluated not only by efficiency or factuality, but also by its abil...
Hoyoung Lee, Suhwan Park, Seung-Han Lee et al.· arXiv.org· 3 citations
When forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, web traffic, and prediction markets - can provide timely signals about firms'operating activities and broader market conditions. These signals may reveal information that...
Jihoon Kwon, Lawrence Liu, Daekyung Park et al.· 0 citations
This paper presents the first systematic empirical study in the financial domain to characterize how an adversarial signal enters a multi-agent trading system and how far it survives toward the decision, and evaluates four communication topologies under data- and agent-level attacks.
CheolWon Na, Hao Ni, Lukasz Szpruch et al.· 0 citations
Fund2Persona, a framework that builds financial-advisor personas from real-world fund disclosures and refines them through an actor-scorer-patcher loop, is proposed, suggesting that real fund data can bring manager-specific investment expertise to LLM advisors rather than merely changing an LLM's surface style.
Suhwan Park, Hoyoung Lee, Zhang-Yang Wang et al.· arXiv.org· 0 citations
