{"paper_id":"2504.14345","title":"LLM-Enhanced Black-Litterman Portfolio Optimization","authors":["Youngbin Lee","Yejin Kim","Juhyeong Kim","Suin Kim","Yongjae Lee"],"paper_date":"2025-04-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2504.14345v2","page_url":"https://thequant.space/flowcharts/llm-enhanced-black-litterman-portfolio-optimization/","scores":{"empirical_rigor":8.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a systematic framework that translates LLM return forecasts and predictive uncertainty into investor views and confidence levels for the Black‑Litterman model.","quote":"This study proposes and validates a systematic framework that translates return forecasts and predictive uncertainty from Large Language Models (LLMs) into the core inputs for the Black-Litterman model: investor views and their confidence levels.","summary":"The Black-Litterman model addresses the sensitivity issues of tra- ditional mean-variance optimization by incorporating investor views, but systematically generating these views remains a key challenge. This study proposes and validates a systematic frame- work that translates return forecasts and…","strategy":"BLM-Llama"},"assumptions":{"status":"available","items":[{"assumption":"Equilibrium returns and covariance are estimated from historical return data.","type":"data","stated":"implied","quote":"When calculating the posterior expected returns μ, we can determine the equilibrium return vector π and the covariance matrix Σ of the stocks from historical return data."},{"assumption":"The hyperparameter τ balances confidence between market equilibrium prior and LLM views.","type":"model","stated":"explicit","quote":"The primary hyperparameter in our framework is τ, which, as introduced in the variance-covariance matrix V in Equation (2), balances the confidence between the market equilibrium prior and the LLM-generated views."},{"assumption":"Transaction costs are 0.1% of portfolio weight changes at each rebalancing.","type":"execution","stated":"explicit","quote":"Costs are calculated as 0.1% of the portfolio weight changes at each rebalancing and are factored into the final performance."},{"assumption":"Portfolio is rebalanced every two weeks.","type":"execution","stated":"explicit","quote":"We run a single backtest over the test period (Sep 2024-Jun 2025), rebalancing the portfolio every two weeks using this fixed τ*."},{"assumption":"The dataset consists of the 50 largest S&P 500 constituents by market cap as of March 26, 2025.","type":"data","stated":"explicit","quote":"We use historical stock price data from the largest 50 S&P 500 constituents by market capitalization as of March 26, 2025, sourced from Yahoo Finance."}]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance S&P 500 constituents price data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"June 2024 to June 2025","universe":"largest 50 S&P 500 constituents","quote":"We use historical stock price data from the largest 50 S&P 500 constituents by market capitalization as of March 26, 2025, sourced from Yahoo Finance. The total dataset spans 13 months, from June 2024 to June 2025.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"3.1 Data Description We use historical stock price data from the largest 50 S&P 500 con-stituents by market capitalization as of March 26, 2025, sourced from Yahoo Finance.","mentions":1,"used_in":1}],"sample":{"start":"2024-09","end":"2025-06","market":"S&P 500 constituents","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"0.1% of the portfolio weight changes at each rebalancing","quote":"Costs are calculated as 0.1% of the portfolio weight changes at each rebalancing and are factored into the final performance.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"0.1% of the portfolio weight changes at each rebalancing","card_quote":"Costs are calculated as 0.1% of the portfolio weight changes at each rebalancing and are factored into the final performance.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"BLM‑Qwen achieved the highest CAGR (0.2811) and BLM‑Llama the second‑highest (0.2751), both surpassing EW (0.1907) and MVO (0.0607).","kind":"performance","quote":"BLM‑Qwen achieved the highest CAGR of 0.2811, closely followed by BLM‑Llama at 0.2751. Both significantly outperformed the traditional benchmarks, EW (0.1907) and MVO (0.0607)."},{"finding":"BLM‑Llama delivered the top annualized Sharpe ratio (1.2286), with BLM‑Qwen second (1.0624), far exceeding EW (0.8937) and MVO (0.2793).","kind":"performance","quote":"In terms of risk‑adjusted returns, measured by the annualized Sharpe Ratio, Sharpe (ann.), BLM‑Llama delivered the top performance with a ratio of 1.2286. BLM‑Qwen secured the second‑highest position at 1.0624. This indicates that both models generated superior excess returns per unit of risk, far exceeding the benchma"},{"finding":"Each LLM exhibits a distinct and consistent investment style that drives performance.","kind":"other","quote":"Crucially, our analysis reveals that each LLM exhibits a distinct and consistent investment style which is the primary driver of performance."},{"finding":"Portfolios using LLM‑generated views significantly outperformed traditional baselines in both absolute and risk‑adjusted terms.","kind":"performance","quote":"Through a backtest on S&P 500 constituents, we demonstrate that portfolios driven by top‑performing LLMs significantly out‑perform traditional baselines in both absolute and risk‑adjusted terms."}],"reported_performance":{"strategy":"BLM-Llama","sharpe":1.2286,"sharpe_benchmark":0.8937,"annual_return_pct":26.27,"total_return_pct":null,"max_drawdown_pct":13.83},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":24,"citations":{"cited_by_in_corpus":4,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":3},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/youngandbin/LLM-BLM","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":"2026-11-14T17:40:39Z"},"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/"}