{"paper_id":"2410.07225","title":"Distilling Analysis from Generative Models for Investment Decisions","authors":["Chung-Chi Chen","Hiroya Takamura","Ichiro Kobayashi","Yusuke Miyao"],"paper_date":"2024-10-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.07225v1","page_url":"https://thequant.space/flowcharts/distilling-analysis-from-generative-models-for-investment-de/","scores":{"empirical_rigor":7,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper introduces three new tasks for modeling professional analysts' decisions and a Chain-of-Decision approach that incorporates an opinion-generator-in-the-loop.","quote":"we propose three tasks to evaluate whether the proposed Chain-of-Decision approach enables models to make decisions like professionals: (1) deciding whether to share the formed opinion with clients, (2) determining if the news alters their initial perspective on the company, and (3) choosing whether to buy or sell the ","summary":"Professionals’ decisions are the focus of every field. For example, politicians’ decisions will influence the future of the country, and stock analysts’ decisions will impact the market. Recognizing the influential role of professionals’ perspectives, inclinations, and actions in shaping…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Professionals’ decisions are predominantly shaped by the most recent news.","type":"model","stated":"explicit","quote":"our approach assumes that professionals’ decisions are predominantly shaped by the most recent news."},{"assumption":"Real‑time, accurate news data is available for the model to predict behavior.","type":"data","stated":"explicit","quote":"Real-time access to accurate and comprehensive news data is necessary for the model to predict the behaviors of professionals effectively."},{"assumption":"The quality and accuracy of the generated opinions affect model performance.","type":"model","stated":"explicit","quote":"our approach relies on the quality and accuracy of the generated opinions."}]},"datasets":{"status":"available","items":[{"name":"A3","provider":"Bloomberg Terminal, Economic Daily News, Commercial Times, T","kind":"text-news","access":"commercial","period":"2014-2020","universe":"Taiwan stock market","quote":"We also obtain news released by two major financial news vendors, Economic Daily News and Commercial Times","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"Due to missing data from Bloomberg Terminal or Taiwan Stock Exchange, some instances were excluded from the analysis as the target companies had been delisted at the time of data collection.","mentions":3,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The Chain-of-Decision approach yields promising improvements in task performance.","kind":"performance","quote":"Our experiments showed promising improvements in the performance of the tasks at hand when employing the CoD approach."},{"finding":"mT5 underperforms on generated analysis but provides the most informative inputs for decision‑making models.","kind":"performance","quote":"although mT5 underperforms when assessed on the generated analysis, it provides the most informative inputs for decision-making models."},{"finding":"Using DAN‑guided ChatGPT improves performance compared to the standard version.","kind":"performance","quote":"we observe enhanced performance when utilizing the DAN-guided ChatGPT, as compared to its standard version."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"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":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T18:00:29Z"},"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/"}