3.1.6 社区摘要 → 全局答案
8 / 8Given a user query, the community summaries generated in the previous step can be used to generate a final answer in a multi-stage process. The hierarchical nature of the community structure also means that questions can be answered using the community summaries from different levels, raising the question of whether a particular level in the hierarchical community structure offers the best balance of summary detail and scope for general sensemaking questions (evaluated in section 4 ).
对于用户给出的查询,可以利用上一步生成的社区摘要,通过多阶段过程形成最终答案。社区结构的层次性也意味着,可以使用不同层级的社区摘要回答问题。由此产生的问题是:对于一般的综合理解问题,社区层次结构中的某一层,是否能够在摘要细节与覆盖范围之间取得最佳平衡?第 4 节对此进行了评估。
For a given community level, the global answer to any user query is generated as follows:
对给定的社区层级,任何用户查询的全局答案按以下方式生成:
Prepare community summaries . Community summaries are randomly shuffled and divided into chunks of pre-specified token size. This ensures relevant information is distributed across chunks, rather than concentrated (and potentially lost) in a single context window.
准备社区摘要:随机打乱社区摘要,再按预先指定的 token 大小切分成块。这样可使相关信息分散到不同文本块中,避免它们集中在单个上下文窗口里,并可能因此丢失。
Map community answers . Intermediate answers are generated in parallel. The LLM is also asked to generate a score between 0-100 indicating how helpful the generated answer is in answering the target question. Answers with score 0 are filtered out.
映射社区答案:并行生成中间答案。同时要求大语言模型给出 0 到 100 的分数,表示生成的答案对于回答目标问题有多大帮助。得分为 0 的答案会被过滤掉。
Reduce to global answer . Intermediate community answers are sorted in descending order of helpfulness score and iteratively added into a new context window until the token limit is reached. This final context is used to generate the global answer returned to the user.
归约为全局答案:按有用性得分从高到低排列中间社区答案,再逐步加入新的上下文窗口,直到达到 token 限额。用这个最终上下文生成返回给用户的全局答案。
本节正文与示例对照,图表及其他章节请查阅原文。译文尚未经人工专业审校。
中间回答得到 95 分之后,你还需要核验什么?
划选正文也可以保存重点。笔记默认仅自己可见,确认公开后才进入共学社区。
模型的有用性分数用于排序,并不是经校准的正确率。精确金额查询是否适合走全局汇总,需要另做比较。