LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation
2026-05-25 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors focus on helping AI write better Introductions for scientific papers by making sure the text is based on the paper's main evidence and follows clear logic. They created a new task called Content-Conditional Introduction Generation (CCIG) and a system named LECTOR that builds a logic graph from the paper's body to guide the writing. LECTOR uses this graph to improve the Introduction’s reasoning and citation accuracy. Their tests on real scientific papers showed improvements in how logical and reliable the Introductions were.
AI-assisted writingIntroduction generationlogic reasoning graphcitation qualityreinforcement learningscientific paper structuretext generationContent-Conditional Introduction Generation (CCIG)
Authors
Jiabei Xiao, Yizhou Wang, Chen Tang, Pengze Li, Wanli Ouyang, Shixiang Tang
Abstract
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.