AI 中文总结
研究针对大语言模型生成退化十二音乐谱的问题，提出神经符号框架，通过生成-验证-修复-追踪循环提升事件局部一致性，经实验该框架提高了交付率和检查通过率，专家盲评显示其生成的作品在多方面更受青睐。
AI 中文摘要
大语言模型能够生成表面合法但会退化为退化纹理的十二音乐谱。我们引入了一种神经符号框架，该框架将语言模型提议器置于带有符号验证的生成-验证-修复-追踪循环中。完整的管道在不要求全曲合法性的情况下提高了事件局部一致性。在40个受控任务和四对模型中，经审核的交付率从原始生成时的13.3%提升至使用该框架时的48.1%。更严格的冲突和序列化一致性检查通过率从33.5%升至58.3%，退化率仍接近0.05。五位专家的盲评也表明，在遵循性、感知合法性、连贯性和整体质量方面，相比原始生成，专家对框架候选作品有明显的总体偏好。
英文摘要
Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures. We introduce a neuro-symbolic harness that wraps a language-model proposer in a generate-verify-repair-trace loop with symbolic verification. The complete pipeline improves event-local consistency without claiming whole-piece legality. Across 40 controlled tasks and four paired models, constraint-checked delivery rises from 13.3% under raw generation to 48.1% with the harness; it abstains on the remaining 51.9% of runs. The pass rate of a narrower collision and serialisation-consistency check rises from 33.5% to 58.3%, while degeneracy remains near 0.05, including under adversarial prompting. A blinded evaluation by five experts also shows a descriptive aggregate preference for harness candidates over raw generation in adherence, perceived legality, coherence, and overall quality.
