AI 中文总结
本研究提出LLM辅助的预处理工作流，通过改写优化中等复杂度金融句子以适配DisCoCat情感分析，经对比实验验证其可降低电路资源消耗并提升准确率，为可扩展QNLP金融情感分析提供探索性依据。
AI 中文摘要
量子自然语言处理（QNLP）为文本建模提供了语法感知框架，分布组合范畴（DisCoCat）是其具有理论基础的公式之一。现有金融情感分析研究已发现DisCoCat的实际局限，包括解析器敏感性、高模拟成本及处理较长句子的难度。本研究提出一种大语言模型（LLM）辅助的预处理工作流，通过可控改写将中等复杂度金融情感句子压缩、简化或分解为解析器兼容且电路高效的变体，同时保留含情感的语义。我们对比了提示策略、语言模型及过滤配置与Stein等人仅含低复杂度句子的DisCoCat基线。在电路层面，最强压缩变体相比原始中等复杂度子集，平均量子比特数和门数减少超70%；在多次训练运行中，采用提示B的GPT-4.1-mini达到最高观测平均准确率，为0.550±0.035，而基线为0.521±0.050。更大的训练集规模未必提升下游性能，在评估配置中，训练集规模与准确率呈中等负相关（皮尔逊相关系数r=-0.446）。这些结果提供了探索性证据：LLM辅助改写可使部分中等复杂度输入在评估的DisCoCat配置中可用，同时凸显提示设计、过滤及电路感知预处理是实现更具可扩展性的基于QNLP的金融情感分析需考虑的因素。
英文摘要
Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, $0.550 \pm 0.035$, compared with $0.521 \pm 0.050$ for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson $r=-0.446$). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis.
