{"paper_id":"2310.04027","title":"Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models","authors":["Boyu Zhang","Hongyang Yang","Tianyu Zhou","Ali Babar","Xiao-Yang Liu"],"paper_date":"2023-10-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2310.04027v2","page_url":"https://thequant.space/flowcharts/enhancing-financial-sentiment-analysis-via-retrieval-augment/","scores":{"empirical_rigor":7.5,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a retrieval‑augmented large language model framework for financial sentiment analysis, combining instruction‑tuned LLMs with external knowledge retrieval.","quote":"retrieval‑augmented large language model framework tailored for financial sentiment analysis.","summary":"Financial sentiment analysis is critical for valuation and investment decision-making. Traditional NLP models, however, are limited by their parameter size and the scope of their training datasets, which hampers their generalization capabilities and effectiveness in this field. Recently, Large…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Financial news and tweets are concise and often lack adequate background information.","type":"data","stated":"explicit","quote":"the typical subjects of financial sentiment analysis, such as news flashes and tweets, are characteristically concise and often lack adequate background information."},{"assumption":"Instruction‑finetuning with a limited set of examples can align LLM predictions with user intentions and boost accuracy.","type":"model","stated":"explicit","quote":"... aligning LLMs’ predictions with user intentions and significantly boosting their prediction accuracy."},{"assumption":"Retrieving additional context based on textual similarity improves sentiment prediction.","type":"model","stated":"implied","quote":"the integration of external knowledge retrieval has further enriched the depth and context of the information fed into the LLMs, enabling more nuanced predictions."},{"assumption":"The approach relies exclusively on textual similarity for retrieval, ignoring macro‑ and micro‑economic data.","type":"other","stated":"explicit","quote":"a limitation of our approach is its exclusive reliance on textual similarity to retrieve relevant information."}]},"datasets":{"status":"available","items":[{"name":"Twitter Financial News dataset","provider":null,"kind":"text-news","access":"public","period":null,"universe":null,"quote":"dataset ... comprises 9,540 samples for training, each annotated with one of three labels: Bearish, Bullish, or Neutral.","known_id":"twitter"},{"name":"FiQA dataset","provider":null,"kind":"text-news","access":"public","period":null,"universe":null,"quote":"FiQA dataset: This dataset includes 961 samples. Each sample has been annotated with one of three labels: positive, neutral, or negative.","known_id":"fiqa"},{"name":"Financial PhraseBank (FPB) dataset","provider":null,"kind":"benchmark","access":"public","period":null,"universe":null,"quote":"comprises 4,840 samples randomly extracted from financial news articles","known_id":"financial-phrasebank"}],"known":[{"id":"financial-phrasebank","name":"Financial PhraseBank","provider":"Malo et al.","kind":"benchmark","access":"public","quote":"We then compare the LLMs including ours and the baselines with and without RAG to further validate the efficacy of RAG. *https://huggingface.co/datasets/financial phrasebank *We utilize Llama-7B for research and education purposes.","mentions":2,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The proposed method achieves a 15% to 48% performance gain in accuracy and F1 score over traditional models and general‑purpose LLMs.","kind":"performance","quote":"achieving a 15% to 48% performance gain in accuracy and F1 score."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"citations":{"cited_by_in_corpus":25,"by_independent_authors":17,"how_cited":{"used_as_baseline":0,"uses_method_or_data":2,"extends":0,"discusses_findings":0,"mentions":10,"unclassified":13},"independent_papers":[{"paper":{"paper_id":"2503.04873","title":"Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?","paper_date":"2025-03-06","authors":["Xinyu Wei","Luojia Liu"],"empirical_rigor":9,"page_url":"https://thequant.space/flowcharts/are-large-language-models-good-in-context-learners-for-finan/"},"how":"uses_method_or_data","quote":null},{"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":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":"2026-11-14T18:21:03Z"},"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/"}