{"paper_id":"2306.14222","title":"Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?","authors":["Haohan Zhang","Fengrui Hua","Chengjin Xu","Hao Kong","Ruiting Zuo","Jian Guo"],"paper_date":"2023-06-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2306.14222v2","page_url":"https://thequant.space/flowcharts/unveiling-the-potential-of-sentiment-can-large-language-mod/","scores":{"empirical_rigor":8,"math_complexity":2,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a standardized experimental procedure that combines sentiment extraction from Chinese news with realistic back‑tests of quantitative trading strategies using three distinct LLMs.","quote":"We propose an innovative approach that combines sentiment extraction with realistic back-tests of quantitative strategies.","summary":"The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies. LLMs excel in analyzing sentiments about listed companies from financial news, providing critical insights for trading decisions. However, the performance…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Portfolios are adjusted daily and only at market open (9:30 am Beijing Time).","type":"execution","stated":"explicit","quote":"Portfolios are adjusted daily and only at market open, 9:30 am Beijing Time (UTC+8:00)"},{"assumption":"Only news generated or acquired before market open are used for sentiment factors.","type":"data","stated":"explicit","quote":"We only use news generated or acquired before market open."},{"assumption":"Trades are executed at the Volume‑Weighted Average Price (VWAP) between 9:30 am and 9:35 am.","type":"execution","stated":"explicit","quote":"we have implemented a more realistic approach by utilizing the Volume-Weighted Average Price (VWAP) between 9:30 am and 9:35 am."},{"assumption":"A transaction fee of 0.15% of transaction value is applied to all trades.","type":"execution","stated":"explicit","quote":"We avoid being overly-optimistic about our simulated returns by imposing a transaction fee of 0.15% of transaction value."},{"assumption":"The CSI 300 index is used as the benchmark for calculating excess returns.","type":"market","stated":"explicit","quote":"We use the CSI 300 index as basis when calculating the excess returns."},{"assumption":"Sentiment scores are mapped to numeric values: GOOD=1, NOT SURE=0, BAD=‑1, and averaged across sources for the same day.","type":"model","stated":"explicit","quote":"We translate the response into numeric values with GOOD NEWS being assigned as 1, NOT SURE being assigned as 0 and BAD NEWS being assigned as -1."}]},"datasets":{"status":"available","items":[{"name":"Chinese news summaries","provider":null,"kind":"text-news","access":"proprietary","period":null,"universe":null,"quote":"We offer Table 1 to illustrate the distribution of these prime sources within our data-set."},{"name":"News summary items","provider":null,"kind":"text-news","access":"proprietary","period":null,"universe":null,"quote":"After the responses for all 394,429 items of news summary have been given."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"0.15% of transaction value (0.05% commission + 0.1% stamp duty) applied to all trades.","quote":"We avoid being overly-optimistic about our simulated returns by imposing a transaction fee of 0.15% of transaction value. This includes a 0.05% commission charged by the stock brokerage firms and a 0.1% stamp duty fee paid to the stock exchanges.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"0.15% of transaction value (0.05% commission + 0.1% stamp duty) applied to all trades.","card_quote":"We avoid being overly-optimistic about our simulated returns by imposing a transaction fee of 0.15% of transaction value. This includes a 0.05% commission charged by the stock brokerage firms and a 0.1% stamp duty fee paid to the stock exchanges.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Erlangshen‑110M outperformed both ChatGPT (GPT‑3.5) and Chinese‑FinBERT on all main performance metrics, achieving the highest annual excess return (24.14%) and Sharpe ratio (0.6841).","kind":"performance","quote":"outperformed GPT‑3.5 across all metrics in this task."},{"finding":"The continuous sentiment score (0‑1) from Erlangshen‑110M provides better differentiation among news items than the discrete three‑level rating used by GPT‑3.5.","kind":"other","quote":"GPT‑3.5 was tasked with returning a discrete sentiment rating from three options (-1, 0, 1), whereas Erlangshen‑110M outputs a continuous score between 0 and 1."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":10,"citations":{"cited_by_in_corpus":10,"by_independent_authors":9,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":7,"unclassified":3},"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":"2026-11-14T18:25:31Z"},"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/"}