T2S-Bench 及 Structure-of-Thought：基准测试与提示的综合文本到结构推理
T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning
AI总结：
本文提出Structure-of-Thought和T2S-Bench，通过显式文本结构化提升模型文本处理性能，实验表明其在多个任务中显著提升准确率。
摘要：
思考人类如何处理复杂阅读任务：标记关键点、推断其关系、并结构化信息以引导理解和响应。同样，大型语言模型能否从文本结构中受益，以增强文本处理性能？为探索这一问题，本文首先引入了Structure of Thought（SoT），一种提示技术，它明确引导模型构建中间文本结构，从而在八个任务和三个模型家族中一致地提升了性能。基于这一洞察，我们提出了T2S-Bench，第一个旨在评估和提升模型文本到结构能力的基准测试。T2S-Bench包含1800个样本，覆盖六个科学领域和32种结构类型，严格构建以确保准确性、公平性和质量。对45种主流模型的评估揭示了显著的改进潜力：在多跳推理任务上的平均准确率仅为52.1%，甚至最先进的模型在端到端提取任务中的节点准确率也只有58.1%。此外，在Qwen2.5-7B-Instruct上，SoT单独在八个不同的文本处理任务上平均提高了5.7%，而进一步在T2S-Bench上微调则将这一收益提高到8.6%。这些结果突显了显式文本结构化的重要性，以及SoT和T2S-Bench的互补贡献。数据集和评估代码已发布在https://t2s-bench.github.io/T2S-Bench-Page/。
英文摘要：
Think about how human handles complex reading tasks: marking key points, inferring their relationships, and structuring information to guide understanding and responses. Likewise, can a large language model benefit from text structure to enhance text-processing performance? To explore it, in this work, we first introduce Structure of Thought (SoT), a prompting technique that explicitly guides models to construct intermediate text structures, consistently boosting performance across eight tasks and three model families. Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models. T2S-Bench includes 1.8K samples across 6 scientific domains and 32 structural types, rigorously constructed to ensure accuracy, fairness, and quality. Evaluation on 45 mainstream models reveals substantial improvement potential: the average accuracy on the multi-hop reasoning task is only 52.1%, and even the most advanced model achieves 58.1% node accuracy in end-to-end extraction. Furthermore, on Qwen2.5-7B-Instruct, SoT alone yields an average +5.7% improvement across eight diverse text-processing tasks, and fine-tuning on T2S-Bench further increases this gain to +8.6%. These results highlight the value of explicit text structuring and the complementary contributions of SoT and T2S-Bench. Dataset and eval code have been released at https://t2s-bench.github.io/T2S-Bench-Page/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
