arXiv subjects

Yu-Shiang Huang

Publications and source records attributed to Yu-Shiang Huang.

4 recordsLinked to original sources

arXiv2026

Detecting Information Channels in Congressional Trading via Temporal Graph Learning

Congressional stock trading has raised concerns about potential information asymmetries and conflicts of interest in financial markets. We introduce a temporal graph network (TGN) framework to identify information channels through which members of Congress may possess advantageous knowledge when trading company stocks. We construct a multimodal dynamic graph integrating diverse publicly available datasets, including congressional stock transactions, lobbying relationships, campaign finance contributions, and geographical connections between legislators and corporations. Our approach formulates the detection problem as a dynamic edge classification task, where we identify trades that exhibit statistically significant outperformance relative to the S&P 500 across long time horizons. To handle the temporal nature of these relationships, we develop a two-step walk-forward validation architecture that respects information availability constraints and prevents look-ahead bias. We evaluate several labeling strategies based on risk-adjusted returns and demonstrate that the TGN successfully captures complex temporal dependencies between congressional-corporate interactions and subsequent trading performance.

cs.CE↗

arXiv2025

Financial Risk Relation Identification through Dual-view Adaptation

A multitude of interconnected risk events -- ranging from regulatory changes to geopolitical tensions -- can trigger ripple effects across firms. Identifying inter-firm risk relations is thus crucial for applications like portfolio management and investment strategy. Traditionally, such assessments rely on expert judgment and manual analysis, which are, however, subjective, labor-intensive, and difficult to scale. To address this, we propose a systematic method for extracting inter-firm risk relations using Form 10-K filings -- authoritative, standardized financial documents -- as our data source. Leveraging recent advances in natural language processing, our approach captures implicit and abstract risk connections through unsupervised fine-tuning based on chronological and lexical patterns in the filings. This enables the development of a domain-specific financial encoder with a deeper contextual understanding and introduces a quantitative risk relation score for transparency, interpretable analysis. Extensive experiments demonstrate that our method outperforms strong baselines across multiple evaluation settings. Our codes are available at https://github.com/cnclabs/codes.fin.relation.

cs.CL↗

arXiv2025

FinNuE: Exposing the Risks of Using BERTScore for Numerical Semantic Evaluation in Finance

BERTScore has become a widely adopted metric for evaluating semantic similarity between natural language sentences. However, we identify a critical limitation: BERTScore exhibits low sensitivity to numerical variation, a significant weakness in finance where numerical precision directly affects meaning (e.g., distinguishing a 2% gain from a 20% loss). We introduce FinNuE, a diagnostic dataset constructed with controlled numerical perturbations across earnings calls, regulatory filings, social media, and news articles. Using FinNuE, demonstrate that BERTScore fails to distinguish semantically critical numerical differences, often assigning high similarity scores to financially divergent text pairs. Our findings reveal fundamental limitations of embedding-based metrics for finance and motivate numerically-aware evaluation frameworks for financial NLP.

cs.CL↗

arXiv2025

Decision-Oriented Text Evaluation

Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as test cases, we assess decision quality based on the financial performance of trades executed by human investors and autonomous LLM agents informed exclusively by these texts. Our findings reveal that neither humans nor LLM agents consistently surpass random performance when relying solely on summaries. However, richer analytical commentaries enable collaborative human-LLM teams to outperform individual human or agent baselines significantly. Our approach underscores the importance of evaluating generated text by its ability to facilitate synergistic decision-making between humans and LLMs, highlighting critical limitations of traditional intrinsic metrics.

cs.CL↗