解决大模型金融预测中的前瞻偏差问题，无需重训即可有效去偏。
A Fast and Effective Solution to the Problem of Look-ahead Bias in LLMs
- 用两个小模型动态调节大模型推理时的输出概率，控制信息保留与遗忘。
- 在不重训的前提下，消除文本和语义层面的知识残留，纠正预测偏差。
- 适合需要快速部署、高成本受限的金融场景应用，如量化交易回测。
将大语言模型应用于金融预测面临前瞻偏差挑战，因其训练数据包含长序列时间信息，导致传统回测方法失效——重新从头训练前沿模型并设置知识截止点成本过高。本文提出一种快速、高效且低成本的替代方案：在推理阶段，通过一对小型专用模型动态调整大模型的输出概率（logits）——一个微调于需遗忘的信息，另一个微调于需保留的信息。实验表明，该方法能有效消除文本级与语义级知识残留，修正模型偏差，性能优于已有方法。
原文摘要 · Abstract (English)
Applying LLMs to predictive tasks in finance is challenging due to look-ahead bias resulting from their training on long time-series data. This precludes the backtests typically employed in finance since retraining frontier models from scratch with a specific knowledge cutoff is prohibitive. In this paper, we introduce a fast, effective, and low-cost alternative. Our method guides generation at inference time by adjusting the logits of a large base model using a pair of smaller, specialized models -- one fine-tuned on information to be forgotten and another on information to be retained. We demonstrate that our method effectively removes both verbatim and semantic knowledge, corrects biases, and outperforms prior methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。