LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation

2026-05-25

AI Summary

Automatically generating scientific paper introductions often suffers from weak logical coherence, citation hallucinations, and misalignment with core evidence. This work proposes LECTOR, a novel framework that formulates the task as content-conditioned introduction generation and introduces scientific reasoning graphs as logical blueprints to guide the writing process. By designing a logic-expression co-reinforcement learning mechanism, LECTOR enables end-to-end joint optimization of reasoning structure and textual generation. Evaluated on a Nature Communications dataset, the method significantly improves reasoning graph quality (+26.7%), citation accuracy (+8.6%), and overall paper consistency (+3.3%), producing introductions that are logically rigorous, reliably cited, and linguistically fluent.

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.

Problem

• scientific paper writing
• introduction generation
• logical reasoning
• citation hallucination
• structured expression

Innovation

• Logic-Expression Co-Reinforcement Learning
• Reasoning Graph
• Introduction Generation
• Scientific Writing
• Citation Faithfulness