PRICE：针对比特币价格预测的大语言模型适配选择的系统性研究
PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
- Isfahan University of Technology（伊斯法罕理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出基于4位量化LLaMA-3 8B的PRICE方法，整合LoRA等技术适配LLMs用于短期比特币价格预测，经对比及消融实验验证其性能优于多数基准模型，凸显适配选择对LLMs数值时间序列预测的关键作用。
AI中文摘要：
加密货币市场呈现出极端的波动性与非平稳动态，对传统预测方法构成挑战。尽管大语言模型（LLMs）在时间序列预测中展现出潜力，但金融场景下适配选择的综合影响仍未得到充分探索。本研究提出PRICE，一种将LLMs适配至短期比特币价格预测的结构化方法，该方法基于4位量化的LLaMA-3 8B模型构建，探究微调、数值表示、提示工程、推理及解码对预测性能的联合影响。PRICE整合了参数高效微调的低秩适配（LoRA）、递归多步推理、整数取整数值表示、上下文-任务-格式（CTF）提示及精确零温度解码。消融研究表明，各组件均对预测精度与可靠性有贡献：LoRA支持在有限硬件上高效训练，递归推理提升精度，整数取整数值降低误差，CTF提示优于思维链、隐式思维链（iCoT）及少样本提示，零温度解码改善递归推理过程中的稳定性。与8种基于Transformer的模型及时间序列基础模型的对比评估显示，PRICE在验证集与测试集上均达到最低预测误差，且在各评估周期中表现稳定。尽管其基于主要在文本而非时间序列数据上预训练的模型，PRICE仍达到了与专用基础模型相当或更优的性能。这些发现表明，适配选择对LLMs在数值时间序列预测中的精度与鲁棒性具有关键决定作用。
英文摘要：
Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language Models (LLMs) have shown promise for time series forecasting, the combined effects of adaptation choices remain largely unexplored in financial settings. This study introduces PRICE, a structured approach for adapting LLMs to short-term Bitcoin price forecasting. Built on a 4-bit quantized LLaMA-3 8B model, PRICE investigates how fine-tuning, numerical representation, prompting, inference, and decoding jointly influence forecasting performance. PRICE integrates Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA), Recursive multi-step inference, Integer-rounded numerical representation, Context-Task-Format (CTF) prompting, and Exact zero-temperature decoding. Ablation studies show that each component contributes to forecasting accuracy and reliability. LoRA enables efficient training on limited hardware, recursive inference improves accuracy, integer-rounded values reduce errors, CTF prompting outperforms Chain-of-Thought, Implicit Chain-of-Thought (iCoT), and few-shot prompting, and zero-temperature decoding improves stability during recursive forecasting. Comparative evaluation against eight transformer-based and time-series foundation models shows that PRICE achieves the lowest forecasting errors on both validation and test sets while maintaining robust performance across evaluation periods. Despite being based on a model primarily pretrained on text rather than time-series data, PRICE achieves competitive or superior performance relative to specialized foundation models. These findings demonstrate that adaptation choices critically determine the accuracy and robustness of LLMs for numerical time-series forecasting.
