发表机构
University College London; University of Warwick（伦敦大学学院; 华威大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出MFAST框架，将金融语言模型输出转化为考虑市场摩擦的交易决策，验证了仅解码器模型在新闻交易中的优越性，并强调端到端工程评估的重要性。
AI 中文摘要
金融语言模型可以将非结构化的公司特定新闻转化为结构化的决策信号，但金融人工智能研究缺乏一个综合部署框架来评估这些信号在金融决策系统中是否仍然有用。计算机科学研究已经开发出用于时间序列预测、文本分类、多模态股票预测、基于图的市场建模和机器学习运维的强有力方法，但这些研究流并未提供一种领域特定的协议，能够在事件时间可观测性、概率校准、执行时机、交易成本、流动性约束、容量限制、运维诊断和统计推断下联合测试金融语言模型的输出。我们引入了MFAST，一个市场摩擦感知的情感到交易框架，它将带时间戳的金融文本转化为可审计、可复现且市场可行的交易决策。该应用是基于新闻的交易，其中公司特定文本必须在评估投资组合决策之前与证券关联。该框架将Refinitiv新闻分析链接到证券价格研究中心（CRSP）股票数据，将主要样本外评估限制在已披露基础模型数据新鲜度期之后的发布新闻，并增加了一个使用开放金融文本和公开价格数据的公共复现分支。结果表明，仅解码器语言模型在分类、校准、收益预测和净投资组合表现方面优于编码器基线和词典情感，而运维诊断揭示了准确性、延迟、内存、吞吐量和推理成本之间的权衡。本文表明，对金融语言模型的可信评估需要一种端到端的工程方法，结合语言理解、时间纪律、市场摩擦感知部署和可复现验证。
英文摘要
Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether those signals remain useful in financial decision systems. Computer science research has developed strong methods for time-series forecasting, text classification, multimodal stock prediction, graph-based market modeling, and machine-learning operations, yet these streams do not provide a domain-specific protocol that jointly tests financial language-model outputs under event-time observability, probability calibration, execution timing, transaction costs, liquidity constraints, capacity limits, operational diagnostics, and statistical inference. We introduce MFAST, a Market-Friction-Aware Sentiment-to-Trading framework that converts timestamped financial text into auditable, reproducible, and market-feasible trading decisions. The application is news-based trading, where firm-specific text must be linked to securities before portfolio decisions can be evaluated. The framework links Refinitiv News Analytics to Center for Research in Security Prices (CRSP) equity data, restricts the primary out-of-sample evaluation to post-release news outside disclosed foundation-model data-freshness periods, and adds a public replication arm using open financial text and public price data. Results show that decoder-only language models outperform encoder baselines and dictionary sentiment in classification, calibration, return prediction, and net portfolio performance, while operational diagnostics reveal trade-offs among accuracy, latency, memory, throughput, and inference cost. The paper shows that credible evaluation of financial language models requires an end-to-end engineering approach combining language understanding, temporal discipline, market-friction-aware deployment, and reproducible validation.
Comments47 pages. Revise and resubmit at Engineering Applications of Artificial Intelligence
