探究大模型推理对摘要生成的影响，发现推理并非万能解药。
Understanding LLM Reasoning for Abstractive Summarization
- 将通用推理策略适配到摘要任务，对比8种策略与3个大推理模型
- 显式推理提升摘要质量但削弱事实一致性，隐式推理则相反
- 增加推理预算未必更好，过度推理反而降低事实准确性
推理显著提升了大语言模型在数学和代码生成等分析任务中的表现，但在抽象摘要生成中的价值尚不明确。为填补这一空白，我们将通用推理策略适配至摘要场景，开展大规模对比实验，涵盖8种推理策略与3个大推理模型（LRMs），在8个不同数据集上评估摘要质量与事实忠实性。结果表明，推理并非普适方案，其效果高度依赖策略选择与任务设置。特别地，我们发现摘要质量与事实忠实性之间存在权衡：显式推理通常提升参考基准下的质量，但可能损害事实基础；而LRM中的隐式推理则呈现相反趋势。此外，增加LRM内部推理预算并未稳定提升摘要表现，甚至可能降低事实一致性。这些发现提示，在摘要任务中，更多推理并不总是更优，有效推理应注重忠实压缩而非过度扩展。源代码已公开。
原文摘要 · Abstract (English)
Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, evaluating both summary quality and factual faithfulness. Our results show that reasoning is not a universal solution and its effectiveness depends strongly on the strategy and the summarization setting. In particular, we find a trade-off between summary quality and factual faithfulness. Explicit reasoning strategies often improve reference-based quality, but may weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. We further find that increasing an LRM's internal reasoning budget does not reliably improve summarization and can even reduce factual consistency. These findings suggest that, for summarization, more reasoning is not always better. Effective reasoning should preserve faithful compression rather than induce over-elaboration. Our source code is publicly available.
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。