解决大模型长文本生成长度不稳问题，提升输出稳定性。
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
- 构建新基准VOLTBench，量化长文本生成的长度波动性。
- 提出GLoBo方法，使输出长度准确率提升148%，波动降低69%。
- 无需训练，轻量级解码优化，适合实际部署场景。
大语言模型在长上下文理解方面表现优异，但在长文本生成中存在显著缺陷：输出长度波动大。现有研究多关注单次生成质量，忽视了这一波动问题，导致计算资源浪费并影响应用可靠性。为此，本文分三阶段展开：首先提出VOLTBench基准，系统量化长文本生成的长度波动；其次通过分析注意力轨迹，揭示引发波动的内部模式；最后提出基于概率分数提升的轻量级解码策略GLoBo，无需额外训练即可显著提升生成长度准确性和稳定性。在VOLTBench上的大量实验首次系统证实主流模型存在严重输出不稳定性，并验证该方法使基础模型平均输出长度提升148%，长度波动降低69%，同时保持高质量生成。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volatility of the output. This volatility not only leads to significant computational costs but also severely impacts the models' reliable application. To address this gap, our work unfolds in three stages: benchmarking, probing, and mitigation. We first propose the VOlatility in Long-form Text Benchmark (VOLTBench), a novel heterogeneous-task benchmark designed to systematically quantify the length volatility of long-form generation. Subsequently, by analyzing attention traces, we conduct an in-depth probe to identify several common internal patterns that cause this volatility. Finally, to mitigate long-form output volatility, we propose Stable Generation via Logits Boosting (GLoBo), a lightweight decoding-stage optimization strategy, designed to significantly enhance both the length accuracy and stability of long-form generation without additional training. Extensive experiments on VOLTBench provide the first systematic confirmation of severe long-form output instability in mainstream models and validate that our proposed method successfully improves the mean output length of the base model by 148% and reduces the length volatility by 69%, while maintaining high generation 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。