用片段级编辑提升分子优化，避免语言模型的幻觉问题
FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimization
- 基于上下文感知的片段排序与替换，替代传统语言生成
- 在多个数据集上超越大模型和图方法，0.6B小模型即达领先性能
- 适合需要高效、可靠分子设计的药物研发人员
分子优化旨在通过微小结构修改改进分子性质，同时保持与原始分子的相似性。现有基于语言模型的方法通常将任务视为提示驱动的序列生成，但依赖自然语言会带来数据扩展瓶颈，易产生化学幻觉，并忽略片段效应的强上下文依赖性。我们提出FORGE，一种两阶段框架，将分子优化重新定义为上下文感知的局部编辑。第一阶段利用自动挖掘并验证的低至高阶编辑对，而非昂贵的人工文本标注，根据完整分子上下文中片段的属性贡献对候选片段进行排序，引入化学先验知识；第二阶段生成明确的片段替换。基于仅0.6B参数的紧凑语言模型，FORGE还能通过上下文示例适应未见过的黑箱目标函数。在Prompt-MolOpt、PMO-1k和ChemCoTBench三个基准上，FORGE持续优于先前方法，包括更大规模的语言模型和图神经网络方法。结果凸显了显式片段级监督作为更易获取、可扩展且无幻觉的替代方案的价值。
原文摘要 · Abstract (English)
Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically treat this task as prompt-conditioned sequence generation. However, relying on natural language introduces an inherent data-scaling bottleneck, often leads to chemical hallucinations, and ignores the strong context dependence of fragment effects. We present FORGE, a two-stage framework that reformulates molecular optimization as context-aware local editing. By utilizing automatically mined, verified low-to-high edit pairs instead of expensive human text annotations, Stage 1 ranks candidate fragments by their property contribution under the full molecular context to inject chemical prior, and Stage 2 generates explicit fragment replacements. Built on a compact 0.6B language model, FORGE further adapts to unseen black-box objectives through in-context demonstrations. Across Prompt-MolOpt, PMO-1k and ChemCoTBench, FORGE consistently outperforms prior methods, including substantially larger language models and graph methods. These results highlight the value of explicit fragment-level supervision as a more easily obtainable, scalable, and hallucination-less alternative to natural language training.
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。