mlsanityData to 14 Oct 2026

Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions

arXiv 2609.23703 ↗First posted 20 Sep 2026cs.CL cs.LG q-fin.TRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 80 references that are in the map. First posted on arXiv 20 Sep 2026.

Builds on

26 of 80 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  6. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  9. 2020Longformer: The Long-Document Transformercited by 3,413
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  12. 2020Big Bird: Transformers for Longer Sequencescited by 1,684
14 more
  1. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  2. 2018Deep learning for time series classification: a reviewcited by 576
  3. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  4. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 348
  5. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  6. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  7. 2023Proving Test Set Contamination in Black Box Language Modelscited by 230
  8. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 222
  9. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 152
  10. 2022WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domaincited by 117
  11. 2023Task Contamination: Language Models May Not Be Few-Shot Anymorecited by 99
  12. 2020Deep Learning for Financial Applications : A Surveycited by 91
  13. 2020Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodologycited by 41
  14. 2022Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networkscited by 13

Built on by

Not cited yet.