{"paper_id":"2509.12519","title":"Context-Aware Language Models for Forecasting Market Impact from Sequences of Financial News","authors":["Ross Koval","Nicholas Andrews","Xifeng Yan"],"paper_date":"2025-09-15","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.12519v1","page_url":"https://thequant.space/flowcharts/context-aware-language-models-for-forecasting-market-impact/","scores":{"empirical_rigor":7.5,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an efficient and effective contextualization method that uses a large language model for the main article and a small language model to encode historical context into summary embeddings aligned with the large model’s space.","quote":"we propose an efficient and effective contextualization method that uses a large LM to process the main article, while a small LM encodes the historical context into concise summary embeddings that are then aligned with the large model’s representation space.","summary":"Financial news plays a critical role in the information diffusion process in financial markets and is a known driver of stock prices. However, the information in each news article is not necessarily self-contained, often requiring a broader understanding of the historical news coverage for accurate…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The binary classification task is evaluated with AUC because continuous scores are more informative for investment management applications.","type":"model","stated":"explicit","quote":"We evaluate the performance on this binary classification task with AUC because the continuous scores are more informative than their discrete predicted classes for investment management applications."},{"assumption":"Transaction costs are estimated and included in the reported investment performance.","type":"execution","stated":"explicit","quote":"Net performance includes an estimate of the impact of transaction costs, detailed in §A.1."},{"assumption":"The most recent N=5 historical articles provide the best context for the main article unless relevance is considered.","type":"data","stated":"explicit","quote":"In the experiments so far, we assume that the N = 5 most recent historical articles about the same company provide the best context for the main article (Time)."},{"assumption":"Historical news articles from FactSet StreetAccount are representative of US‑based publicly‑traded companies’ information flow.","type":"data","stated":"explicit","quote":"We collect stock-specific financial news articles in English from FactSet StreetAccount for US-based publicly-traded companies."}]},"datasets":{"status":"available","items":[{"name":"FactSet StreetAccount news","provider":"FactSet","kind":"text-news","access":"commercial","period":"2010-2023","universe":"US publicly‑traded companies","quote":"We collect stock-specific financial news articles in English from FactSet StreetAccount for US-based publicly-traded companies. These articles cover a variety of events and news sources.","known_id":"factset"}],"known":[{"id":"factset","name":"FactSet","provider":"FactSet","kind":"fundamentals","access":"commercial","quote":"Data Acquisition and Curation We collect stock-specific financial news articles in English from FactSet StreetAccount for US-based publicly-traded companies.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Costs are estimated and incorporated into net portfolio returns; see §A.1 for the specific model.","quote":"Net performance includes an estimate of the impact of transaction costs, detailed in §A.1.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Costs are estimated and incorporated into net portfolio returns; see §A.1 for the specific model.","card_quote":"Net performance includes an estimate of the impact of transaction costs, detailed in §A.1.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Historical context provides a consistent and significant improvement in performance across methods and time horizons.","kind":"performance","quote":"We find that historical context provides a consistent and significant improvement in performance across methods and time horizons."},{"finding":"Increasing the number of historical context articles improves forecasting performance and reduces LM loss up to about 15 articles, with diminishing returns after 10.","kind":"performance","quote":"The results provide evidence towards our hypothesis that model performance on our task demonstrates language understanding as we find that both forecasting performance and LM loss improves with the number of contexts incorporated."},{"finding":"All contextualization methods provide a material benefit over their corresponding single‑article baselines, with summarization approaches outperforming simple concatenation.","kind":"performance","quote":"While we find that all contextualization methods provide a material benefit over their corresponding single-article baselines, we find that approaches that summarize the relevant context into a more concise and informative form"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":12,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/rosskoval/calm_fin_news","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:27:06Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}