FIDES：一种针对大语言模型生成交易策略的一致性协议
FIDES: A Concordance Protocol for LLM-Generated Trading Strategies
查看机构详情
- DGrid AI
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
FIDES是针对LLM生成交易策略的一致性测量协议，通过三类产物的一致性打分发现一致性不预测收益、自我评估校准不足等关键结果，为测量保真度提供方案。
中文摘要 AI 辅助
当向大语言模型（LLM）请求交易策略时，会同时生成三类产物：自然语言逻辑说明、可执行代码实现，以及运行后得到的业绩记录。但很少有人检查这些产物是否对应同一策略。我们提出FIDES，一种将这三类产物视为需协调的三个视图而非单一待评估交付物的测量协议。通过双重交付，单次模型调用会同时返回带有明确宣称优势的自然语言策略，以及自包含的策略（df）函数。FIDES在沙箱中执行代码，采用滞后一期的样本外回测，并对三类一致性差距打分：宣称要做的、实际执行的、结果的一致性。针对8种流动性美国ETF、4个模型加两阶段引导分支、40个2023至2024年样本外策略，得出三项关键发现：其一，一致性无法预测收益：40个策略中仅2个跑赢买入持有策略，简单的sma(50,200)规则跑赢所有模型的平均夏普比率；其二，自我评估校准严重不足：40个策略中32个宣称跑赢买入持有策略，但仅1个实现；其三，将语言代码判断替换为第二个模型，会在超过半数项目上反转“宣称要做”的结果。注入该URL（-1）使“执行与实际”的一致性平均下降0.33，而我们的运行时未来信息探测在干净代码和注入代码中均未触发。我们将FIDES定义为测量保真度的协议，而非对市场表现的主张。
英文摘要
An LLM asked for a trading strategy returns three artifacts at once: a natural-language rationale, an executable implementation, and once run, a track record. Whether these are the same object is rarely checked. We present FIDES, a measurement protocol that treats them as three views to be reconciled rather than one deliverable to be graded. Through dual delivery, a single model call returns both a natural-language strategy with an explicit claimed edge and a self-contained strategy(df) function. FIDES executes the code in a sandbox against a lag-one out-of-sample backtest and scores three concordance gaps: say to do, do to real, and say to result. On 8 liquid US ETFs across four models plus a two-stage elicitation arm, 40 strategies, 2023 to 2024 out-of-sample, three findings stand out. First, concordance does not predict profit: only 2 of 40 strategies beat buy-and-hold, and a plain sma(50,200) rule outperforms every model's mean Sharpe. Second, self-assessment is badly calibrated: 32 of 40 strategies claim to beat buy-and-hold and exactly one does. Third, swapping the language-code judge for a second model flips say to do on more than half of items. Injecting Close.shift(-1) drops do to real by 0.33 on average, while our runtime future-information probe fired on neither clean nor injected code. We frame FIDES as a protocol for measurement fidelity, not a claim about market performance.
