{"paper_id":"2401.11011","title":"BioFinBERT: Finetuning Large Language Models (LLMs) to Analyze Sentiment of Press Releases and Financial Text Around Inflection Points of Biotech Stocks","authors":["Valentina Aparicio","Daniel Gordon","Sebastian G. Huayamares","Yuhuai Luo"],"paper_date":"2024-01-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.11011v1","page_url":"https://thequant.space/flowcharts/biofinbert-finetuning-large-language-models-llms-to-analy/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes BioFinBERT, a finetuned large language model for financial sentiment analysis of biotech press releases.","quote":"Here, we present BioFinBERT, a finetuned LLM to perform financial sentiment analysis of public text associated with stocks of companies in the biotechnology sector.","summary":"Large language models (LLMs) are deep learning algorithms being used to perform natural language processing tasks in various fields, from social sciences to finance and biomedical sciences. Developing and training a new LLM can be very computationally expensive, so it is becoming a common practice…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trading entries are triggered when the price difference between Open and Close on the release day exceeds 5%.","type":"execution","stated":"explicit","quote":"The benchmark trading strategy consists in entering a position based on a 5% threshold difference between the Open and Close price on the release day, or the next trading day if the press release wasn’t published on a trading day."},{"assumption":"Positions are held for fixed periods of 1, 2, or 3 months after a positive event.","type":"execution","stated":"explicit","quote":"Specifically, our trading strategy implied holding biotech stocks following a positive event for 1, 2, or 3 months after the event’s announcement."}]},"datasets":{"status":"available","items":[{"name":"financial_phrasebank","provider":"HuggingFace","kind":"text-news","access":"public","period":null,"universe":null,"quote":"For our first attempt at finetuning BioBERT, we used the financial_phrasebank dataset from HuggingFace, which contains ~4,000 samples of financial news sentiment classification already attributed with positive, negative, or neutral labels."},{"name":"FiQA financial text sentiment dataset","provider":"Kaggle","kind":"text-news","access":"public","period":null,"universe":null,"quote":"we added the FiQA financial text sentiment dataset from Kaggle.","known_id":"kaggle"},{"name":"Biopharma‑Dive curated dataset","provider":"BioPharma‑Dive news publisher","kind":"text-news","access":"public","period":null,"universe":"biotech companies","quote":"Our third attempt was to curate our own dataset to combine with financial_phrasebank to finetune BioBERT. This dataset was obtained from 96 news articles from the biotech section of BioPharma-Dive news publisher."},{"name":"NASDAQ Biotechnology Index (NBI)","provider":"NASDAQ","kind":"benchmark","access":"public","period":"2020-2023","universe":"biotech stocks","quote":"Our market benchmark was the NASDAQ Biotechnology Index (NBI) and the back-testing period was between 2020 and 2023."}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"We gathered stock prices from Yahoo Finance and determined whether the event associated with the press release was (i) positive, corresponding to significant stock price upward change, (ii) neutral, corresponding Large-cap Mid-cap Small-cap Micro-cap Positive > 1% > 2% > 3% > 4% Negative < -1% < -2% < -3% < -4% Neutral -1% ~ 1% -2% ~ 2% -3% ~ 3% -4% ~ 4% Table 1: Classification of positive, negative,","mentions":3,"used_in":2},{"id":"fiqa","name":"FiQA","provider":"FiQA challenge","kind":"benchmark","access":"public","quote":"In addition to the financial_phrasebank from HuggingFace used earlier, we added the FiQA financial text sentiment dataset from Kaggle.","mentions":1,"used_in":1},{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"In addition to the financial_phrasebank from HuggingFace used earlier, we added the FiQA financial text sentiment dataset from Kaggle.","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":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The finetuned BioBERT (BioFinBERT) achieved an F1 score of 0.9104, validation loss of 0.7088, and success rate of 62.86%, comparable to FinBERT.","kind":"predictive-accuracy","quote":"Ultimately, this finetuned BioBERT performed similarly to FinBERT for an F1 score of 0.9104, validation evaluation loss of 0.7088, and success rate of 62.86%."},{"finding":"For a 1‑month holding period, micro‑cap stocks following a positive event delivered the best performance among market‑cap categories.","kind":"performance","quote":"For a 1-month holding period, holding micro-cap stocks following a positive event had the best performance, and holding l…"},{"finding":"The BioPharma strategy yields the highest annualized Sharpe Ratio for Large‑Cap companies, while FinPhrase is best for Mid‑Cap and the benchmark for Small‑ and Micro‑Cap.","kind":"performance","quote":"BioPharma strategy works best for Large-Cap companies • FinPhrase strategy works best for Mid-Cap companies •"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":12,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":2},"independent_papers":[{"paper":{"paper_id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","paper_date":"2024-06-15","authors":["Yuqi Nie","Yaxuan Kong","Xiaowen Dong","John M. Mulvey","H. Vincent Poor","Qingsong Wen"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/a-survey-of-large-language-models-for-financial-applications/"},"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":true,"code_url":"https://huggingface.co/datasets/daniel-gordon/biopharma-dive","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":"2026-11-14T18:16:13Z"},"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/"}