训练稳定反而让大模型生成内容单调重复，值得警惕。
Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs
- 用最大似然训练时，稳定参数轨迹会最小化前向KL散度，压缩生成熵。
- 实验证明稳定训练导致输出熵低、重复率高，跨架构和随机种子一致。
- 适合关注模型生成多样性与优化稳定性关系的研究者阅读。
训练稳定性通常被视为大语言模型可靠优化的前提。本文分析了稳定训练动态如何影响生成分布。在标准最大似然训练下，稳定的参数轨迹使模型近似最小化前向KL散度至经验分布，同时隐式降低生成熵。结果是模型将概率质量集中在经验分布的有限子集上，表现出系统性退化，尽管损失平滑收敛。我们通过基于反馈的受控训练框架验证此现象，该框架稳定内部生成统计量，观察到所有架构和随机种子下均出现低熵输出与重复行为。这表明优化稳定性与生成表达能力并非天然一致，仅靠稳定性无法保证生成质量。
原文摘要 · Abstract (English)
Training stability is typically regarded as a prerequisite for reliable optimization in large language models. In this work, we analyze how stabilizing training dynamics affects the induced generation distribution. We show that under standard maximum likelihood training, stable parameter trajectories lead stationary solutions to approximately minimize the forward KL divergence to the empirical distribution, while implicitly reducing generative entropy. As a consequence, the learned model can concentrate probability mass on a limited subset of empirical modes, exhibiting systematic degeneration despite smooth loss convergence. We empirically validate this effect using a controlled feedback-based training framework that stabilizes internal generation statistics, observing consistent low-entropy outputs and repetitive behavior across architectures and random seeds. It indicates that optimization stability and generative expressivity are not inherently aligned, and that stability alone is an insufficient indicator of generative quality.
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。