LECTOR: 科学推理图与引言生成的联合优化
LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation
AI总结:
提出LECTOR框架,通过逻辑-表达协同强化学习联合优化科学推理图的结构保真度和引言生成质量,在Nature Communications数据集上实现显著提升。
摘要:
AI科学家在研究流程的多个阶段已展现出有希望的进展,其中自动科学论文写作仍然是一个艰巨的挑战。引言写作尤其困难,不仅要求语言流畅,还需要逻辑合理性和可验证的忠实性。大多数AI辅助方法将任务视为文本生成而非推理和结构化,导致严重缺陷,例如引用幻觉。为解决此问题,我们首先定义了内容条件引言生成(CCIG)任务,要求引言基于论文的核心证据。然后我们提出LECTOR,一种新颖的逻辑-表达协同强化学习框架,能够严格遵循科学家的逻辑,添加高质量引用并保持结构化表达。LECTOR首先从论文主体构建逻辑推理图,作为可验证的逻辑蓝图。随后,它采用逻辑-表达协同奖励机制,联合优化图的结构保真度和最终叙述的质量。我们从Nature Communications论文中构建数据集来评估我们的方法。大量实验表明,在逻辑保真度和引言生成质量指标上均有一致改进,例如图质量(+26.7%)、引用质量(+8.6%)和论文一致性(+3.3%)。代码和数据可在https://github.com/Xiao-Youth/LECTOR获取。
英文摘要:
AI Scientists have shown promising progress across multiple stages of the research pipeline, among which automatic scientific paper writing remains a formidable challenge. The Introduction writing is especially challenging, which demands not only linguistic fluency, but logical soundness and verifiable faithfulness. Most AI-assisted methods treat the task as text generation instead of reasoning and structuring, leading to severe drawbacks, e.g., hallucinating citations. To address this, we first formulate the Content-Conditional Introduction Generation (CCIG) task, which requires grounding the Introduction in the paper's core evidence. We then propose LECTOR, a novel Logic-Expression Co-Reinforcement Learning framework that can strictly follow the scientist's logic, add high-quality citations and keep structured expressions. LECTOR first constructs a logic-reasoning graph from the paper's main body to serve as a verifiable logical blueprint. Subsequently, it employs a Logic-Expression Co-Rewarding mechanism to jointly optimize for both the graph's structural fidelity and the final narrative's quality. We conduct a dataset from Nature Communications papers to assess our method. Extensive experiments show consistent improvements in both logic fidelity and Introduction generation quality metrics, e.g., Graph Quality (+26.7%), Citation Quality (+8.6%), and Paper Consistency (+3.3%). Code and data are available at https://github.com/Xiao-Youth/LECTOR.
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。