大规模事实核查：构建更准确、更高效的摘要事实性系统

Introduction

引言

Picture this — you’re home after a long day at work and can’t wait to catch up on Bridgerton. You log on to Netflix, search for “Bridgerton” and land on this screen:

想象一下——漫长的一天工作后，你回到家，迫不及待地想追看《布里奇顿》。你登录 Netflix，搜索“Bridgerton”，然后来到这个页面：

If this sounds familiar, you already know what a synopsis is — it’s a short glimpse into what a viewer can expect to see in a show. We see two types of synopses here: a series-level synopsis describing the overarching plot, and multiple episode-level synopses describing each episode.

如果这听起来很熟悉，那你就已经知道什么是剧情简介了——它让观众快速一瞥一部剧集会看到什么。这里我们见到两类剧情简介：一类是剧集级剧情简介，描述整体剧情；另一类是多个单集级剧情简介，分别描述每一集。

A synopsis plays a very important role for us — it helps viewers decide whether a title is worth watching or not. Every synopsis needs to strike a balance: sharing just enough to give viewers a sense of what to expect, while leaving enough intrigue to draw them in. But of course, we can’t just write anything.

剧情简介对我们来说非常重要——它帮助观众决定一部作品是否值得观看。每篇剧情简介都需要取得平衡：分享刚好足够的信息，让观众对内容有所预期，同时保留足够的悬念来吸引他们。当然，我们不能随便写任何东西。

“In the fog-drenched streets of Victorian London, Detective Daphne Bridgerton races to unmask a serial killer known only as the elusive Lady Whistledown.”

“在雾气弥漫的维多利亚时代伦敦街头，侦探达芙妮·布里奇顿争分夺秒，要揭开一名连环杀手的真面目，此人只以神秘莫测的惠斯尔顿夫人之名而为人所知。”

Intriguing? Definitely. But it is most certainly not the premise of Bridgerton. Which leads us to the first (and most important) rule of writing a good synopsis: it must be factual. At Netflix’s scale, with thousands of titles, multiple episodes per season and multiple languages, fact-checking all of these by hand simply doesn’t scale. This is where our factuality service comes in: an automated way to judge whether a synopsis is factual or not.

引人入胜？当然。但这绝对不是《布里奇顿》的剧情设定。这就引出了撰写优质剧情简介的第一条（也是最重要的一条）规则：它必须符合事实。在 Netflix 这样的规模下，拥有数千部作品、每季多集以及多种语言，人工核查所有这些内容根本无法规模化。这正是我们的事实性服务发挥作用的地方：一种自动判断剧情简介是否符合事实的方法。

Our current factuality checker feeds a reasoning model everything we know about a title (like metadata and text assets) and asks it to judge synopsis factuality accor...