通过动态惩罚重复内容，让大模型生成更多元的多分支故事。
Avoidance Decoding for Diverse Multi-Branch Story Generation
- 用双重惩罚机制控制概念与叙事相似性，分阶段提升多样性
- 相比强基线，输出多样性提升2.6倍，重复率平均降低30%
- 适合需要创意发散的文本生成任务，如故事创作、内容扩展
大型语言模型在故事生成等任务中常因输入相同而产生重复单调的输出。为此，我们提出一种新型解码策略——规避解码（Avoidance Decoding），通过惩罚与已生成内容的相似性来引导更丰富的多分支故事生成。该策略自适应地平衡两种相似性度量：早期优先采用概念级相似性惩罚以拓展初始故事构思，后期逐步强化叙事级相似性惩罚以保证情节自然且多样。实验表明，该方法相较强基线实现最高达2.6倍的输出多样性提升，重复率平均下降30%，同时有效缓解文本退化问题。此外，我们发现该方法激活了更广泛的神经元，表明其能激发模型内在创造力。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often generate repetitive and monotonous outputs, especially in tasks like story generation, due to limited creative diversity when given the same input prompt. To address this challenge, we propose a novel decoding strategy, Avoidance Decoding, that modifies token logits by penalizing similarity to previously generated outputs, thereby encouraging more diverse multi-branch stories. This penalty adaptively balances two similarity measures: (1) Concept-level Similarity Penalty, which is prioritized in early stages to diversify initial story concepts, and (2) Narrative-level Similarity Penalty, which is increasingly emphasized later to ensure natural yet diverse plot development. Notably, our method achieves up to 2.6 times higher output diversity and reduces repetition by an average of 30% compared to strong baselines, while effectively mitigating text degeneration. Furthermore, we reveal that our method activates a broader range of neurons, demonstrating that it leverages the model's intrinsic creativity.
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。