{"paper_id":"2305.07972","title":"Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis","authors":["Agam Shah","Suvan Paturi","Sudheer Chava"],"paper_date":"2023-05-13","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2305.07972v1","page_url":"https://thequant.space/flowcharts/trillion-dollar-words-a-new-financial-dataset-task--marke/","scores":{"empirical_rigor":6,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper introduces a large tokenized, annotated FOMC text dataset, a hawkish‑dovish classification task, an aggregate monetary policy stance measure, and a simple trading strategy that outperforms the QQQ benchmark.","quote":"We construct the largest tokenized and annotated dataset of FOMC speeches, meeting minutes, and press conference transcripts in order to understand how monetary policy influences financial markets.","summary":"Monetary policy pronouncements by Federal Open Market Committee (FOMC) are a major driver of financial market returns. We construct the largest tokenized and annotated dataset of FOMC speeches, meeting minutes, and press conference transcripts in order to understand how monetary policy influences…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trading results are reported without transaction fees, assuming low‑frequency trading incurs negligible costs.","type":"execution","stated":"explicit","quote":"In our trading strategy construction, we do not include transaction fees as it involves low-frequency trading."},{"assumption":"Sentence splitting is performed using a simple rule‑based approach, assuming this is sufficient for handling opposite tones.","type":"data","stated":"explicit","quote":"In dataset construction, while splitting sentences, we use a simple rule-based approach."}]},"datasets":{"status":"available","items":[{"name":"FOMC Meeting Minutes","provider":"Federal Reserve","kind":"text-news","access":"public","period":"1996-2022","universe":null,"quote":"Meeting Minutes 1996 - 2022 214 44,923 1,346,674 29.98"},{"name":"FOMC Press Conferences","provider":"Federal Reserve","kind":"text-news","access":"public","period":"2011-2022","universe":null,"quote":"Meeting Press Conferences 2011-2022 63 19,068 468,941 24.59"},{"name":"FOMC Speeches","provider":"Federal Reserve","kind":"text-news","access":"public","period":"1996-2022","universe":null,"quote":"Speeches 1996-2022 1,026 108,463 3,222,285 29.71"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"QQQ Index We collect the adjusted closing in-dex price of QQQ from Yahoo Finance5.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"In our trading strategy construction, we do not include transaction fees as it involves low-frequency trading.","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"In our trading strategy construction, we do not include transaction fees as it involves low-frequency trading.","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Finetuned PLMs, especially RoBERTa‑large, outperform rule‑based and LSTM models by a significant margin across all datasets.","kind":"performance","quote":"Finetuned PLMs outperform rule-based model and LSTM models by a significant margin."},{"finding":"The constructed monetary policy stance measure shows statistically significant correlations with CPI and PPI changes.","kind":"statistical","quote":"Table 6: Correlation of immediate next CPI and PPI data with our measure. All values are statistically significant."},{"finding":"A simple trading strategy based on the stance measure outperforms the QQQ index benchmark over the last decade.","kind":"performance","quote":"We also propose a simple trading strategy that outperforms the high benchmark set by the QQQ index over the last decade."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":9,"by_independent_authors":8,"how_cited":{"used_as_baseline":0,"uses_method_or_data":3,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":4},"independent_papers":[{"paper":{"paper_id":"2408.11878","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","paper_date":"2024-08-20","authors":["Jimin Huang","Mengxi Xiao","Dong Li","Zihao Jiang","Yuzhe Yang","Yifei Zhang"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/open-finllms-open-multimodal-large-language-models-for-fina/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2412.10906","title":"SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation","paper_date":"2024-12-14","authors":["Qilong Wu","Xiaoneng Xiang","Hejia Huang","Xuan Wang","Yeo Wei Jie","Ranjan Satapathy"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/susgen-gpt-a-data-centric-llm-for-financial-nlp-and-sustain/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2502.18471","title":"FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data","paper_date":"2025-02-04","authors":["Ankur Sinha","Chaitanya Agarwal","Pekka Malo"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/finbloom-knowledge-grounding-large-language-model-with-real/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:26:53Z"},"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/"}