{"paper_id":"2308.14634","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","authors":["Lefteris Loukas","Ilias Stogiannidis","Prodromos Malakasiotis","Stavros Vassos"],"paper_date":"2023-08-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2308.14634v1","page_url":"https://thequant.space/flowcharts/breaking-the-bank-with-chatgpt-few-shot-text-classification/","scores":{"empirical_rigor":6.5,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes using conversational GPT models for easy and quick few-shot text classification in finance and fine‑tuning masked language models with SetFit to achieve state‑of‑the‑art results.","quote":"We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset.","summary":"We propose the use of conversational GPT models for easy and quick few-shot text classification in the financial domain using the Banking77 dataset. Our approach involves in-context learning with GPT-3.5 and GPT-4, which minimizes the technical expertise required and eliminates the need for…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Limited label availability in financial datasets makes few‑shot methods necessary.","type":"data","stated":"explicit","quote":"our proposed methods offer a practical solution for few-shot tasks in datasets with limited label availability"},{"assumption":"Subscription fees for GPT APIs may be costly for small organizations.","type":"execution","stated":"explicit","quote":"subscription fees associated with these solutions may be considered costly for small organizations"},{"assumption":"Token limits restrict the number of examples that can be shown to the model (e.g., 3 samples).","type":"model","stated":"explicit","quote":"often have limited token capacity, which only allows us to show the model 3 samples, for example"},{"assumption":"Human‑curated representative samples improve in‑context learning performance.","type":"model","stated":"explicit","quote":"using our human-curated representative samples leads to better in‑context learning results"}]},"datasets":{"status":"available","items":[{"name":"Banking77","provider":"PolyAI","kind":"text-news","access":"public","period":null,"universe":null,"quote":"... a real-life dataset of customer service intents and their classification labels"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R4a","candidates":{"front_matter":"n/a","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Experiments cost around $60 with GPT‑3.5 and $1,480 with GPT‑4 due to API token pricing.","card_quote":"Our experiments cost around 60$ when using GPT‑3.5 ($0.002 per 1K tokens) and 1,480$ when using GPT‑4 ($0.03 per 1K tokens for the 8K context model).","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"GPT‑3.5 in a 1‑shot setting outperforms S‑MPNet‑v2 and P‑MPNet‑v2 by over 17 percentage points.","kind":"performance","quote":"GPT‑3.5 achieves competitive results despite the fact that it is presented with only 1 sample per class"},{"finding":"GPT‑4 in a 3‑shot setting outperforms all other models by more than 6 percentage points.","kind":"performance","quote":"GPT‑4 also shows potential for few‑shot text classification, outperforming all other models on the 3‑shot setting by more than 6 pp"},{"finding":"In the 10‑shot setting, S‑MPNet‑v2 beats the previous state‑of‑the‑art by 2.2 percentage points.","kind":"performance","quote":"the previous state‑of‑the‑art ... in the 10‑shot setting (by"},{"finding":"Using human‑curated representative samples yields better in‑context learning results than random samples.","kind":"predictive-accuracy","quote":"using our human-curated representative samples leads to better in‑context learning results"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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":"2026-11-14T18:22:54Z"},"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/"}