FlowingFlowing
← 返回全部开发案例
开发阶段案例 · 模型盲评尚待独立人工复核，不代表正式 Benchmark 结论。
自动补全评审未完成16 / 162 · 17c04c10cafd0d5e

A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges

定量生物学 · 2306.15890v1

FLOWING EVIDENCE BENCHMARK

怎么判断 Evidence 真的有帮助？

核心问题是：在同一写作位置、使用同一模型和任务时，提供检索文献片段会怎样改变首次输出？我们成对比较两种条件，保留持平、不可用和评审未完成的结果。

同一段原稿 · 比较是否提供 Evidence

01 · 固定写作位置

论文原稿

同一处写作点位 ▌

同一原稿位置的自动补全成对比较

02 · 构造两组输入

两组共用

原稿上下文、模型、任务和提示词

A · 提供 Evidence

额外提供检索文献片段

B · 不提供 Evidence

不提供检索文献片段

LLM

同一模型、同一版本

A → 首次输出

B → 首次输出

盲评 Agent

匿名标记两份首次输出为 X、Y

按续写质量判断：准确性、任务贴合度和可用性
输出：X 更优 / 持平 / Y 更优 / 两组均不可用

换序复评：X / Y → Y / X

盲评具体怎么判？

① 匿名两份输出
评审看到同一原稿和两份首次输出，但不知道哪份用了 Evidence。

② 比较并换序复评
根据当前任务的标准，按 X/Y、再按 Y/X 的顺序各评一次。

③ 复核分歧
两次结论不一致时再做第三次判定；未完成的评审也留在分母。

自动补全点位怎样分层？

在查看生成结果前，先核查检索片段是否含有能直接支撑下一步续写的具体命题；有则放在左侧机会组，否则放在右侧普通组。每个学科从可准入论文中均衡选取两组点位。50/50 是实验设计，不代表真实写作中两类点位各占一半。

AUTOCOMPLETE · 110

定量生物学、统计学、天体物理学

左侧 55 个、右侧 55 个点位；统计学采用 10 篇论文的复测结果。

AUTOCOMPLETE · 52

心理学与气候科学

左侧 26 个、右侧 26 个点位；心理学计入 9 篇，气候科学计入 4 篇。

表格里的百分比怎么算？

五学科共有 81 个左侧点位，其中 51 个点位的 Evidence 版本获评更优。持平、两组均不可用和评审未完成的点位仍计入分母。

51Evidence 版本更优
÷
81该层全部点位
=
63%该层 Evidence 获评更优的比例

来源贡献是另一项复核：已进入复核的 22 个 Evidence 获胜点位中，16 个确认直接使用了检索论文；另有 29 个胜出点位尚待复核。

当前是开发阶段的模型评审结果，尚未完成独立人工复核；这些数字不代表正式 Benchmark 结论，也不能单独证明因果关系。

原稿写作位置

原文摘录 · 非 PDF 页面

研究论文 · 原文片段

A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges

5 Conclusion and Future Directions > 5.3 Non-autoregressive Modeling

…xplored. 3D position vectors provide important complementary distance information for each pair of atoms. The relative pairwise distance can be very different in 3D Euclidean geometry compared to 2D molecular graphs. For example, atom v 1 v_{1} and atom v 2 v_{2} may be distant from each other in a non-euclidean molecular graph while they might be close to each other in 3D Euclidean space. This is particularly useful for reaction center ranking. Therefore, effectively incorporating 3D molecular information into modeling can facilitate the more accurate reaction and retrosynthesis predictions.

…as scaffold split and time split, should be included for cross-validation. For retrosynthesis prediction, the USPTO-50K dataset is at small-scale. A new benchmark dataset should be a large-scale dataset containing at least 100K samples. Furthermore, future benchmark datasets should contain more target molecules with multiple edits. In addition, a new evaluation metric for retrosynthesis is necessary and urgent. FusionRetro Liu et al. 2023 attempts to evaluate single-step retrosynthesis models in the context of multi-step planning. More diverse evaluation metrics can be designed in the future.

↓ 此处生成下一段续写

黄色标出写作点位附近的原文；本页根据评测输入重排文本，不是原始 PDF 截图。

同一写作位置的成对对照盲评结果：评审未完成

两组使用同一模型、同一写作任务和原稿上下文，仅比较是否提供检索文献片段。下方展示评测记录中的首次输出。

Evidence

同一模型与写作位置 · 提供检索文献片段 · 首次输出

Non-autoregressive modeling offers a promising alternative to the sequential decoding paradigm that dominates reaction and retrosynthesis prediction. By generating the reaction outcome or precursor set in a single pass rather than token by token, such approaches can avoid the exposure bias and error accumulation inherent to autoregressive decoders, while permitting parallel prediction of multiple reaction centers. Realizing these benefits, however, requires architectures that can capture the joint dependencies among simultaneously predicted outputs, which remains an open challenge for the field.

提供给 Evidence 版本的文献片段

Metro: Memory-Enhanced Transformer for Retrosynthetic Planning via Reaction Tree

These approaches have the following limitations: 1) the training dataset of single-step reactions limits the understanding of the transformation of organic molecules as a sequence of chaining chemical reactions. 2) past works use single-step retrosynthesis models, which neglect the context informati…

展开完整文献摘录

These approaches have the following limitations: 1) the training dataset of single-step reactions limits the understanding of the transformation of organic molecules as a sequence of chaining chemical reactions. 2) past works use single-step retrosynthesis models, which neglect the context information in the reaction tree. 3) the test set is too small to comprehensively evaluate the performance. 4) the evaluation unit of existing benchmark is the reaction route which is one path from the root node to the leaf node in the reaction tree.

无 Evidence

同一模型与写作位置 · 不提供检索文献片段 · 首次输出

Non-autoregressive modeling offers a promising alternative to the sequential decoding paradigm that dominates current reaction and retrosynthesis prediction. By generating the complete set of reaction edits in a single pass rather than one token at a time, such approaches can avoid the error accumulation and inference latency inherent to autoregressive decoding, and they align naturally with the graph-structured nature of chemical reactions.

模型盲评结论

评审未完成，因此此案例没有胜负结论，但仍计入上方统计的分母。

文献片段是输入材料；出现于此不代表输出使用了它，也不代表它能够支持全部主张。原文与检索片段经过截取；页面没有展示模拟分数或模拟 PDF。