The types of hard problems @EngramLab works on ft. co-founder @dan_biderman: "Clients do financing,...
TL;DR · AI 摘要
EngramLab通过合成数据集解决法律领域RAG技术瓶颈，Harvey开源的100M+令牌合成律所数据可评估代理搜索能力。
核心要点
- RAG技术无法处理非结构化法律文件中的隐性信息，需人工逐文件核查
- Harvey开源的合成律所包含46个客户10k文件，覆盖250+案件
- 法律科技领域需结合合成数据与人工验证解决复杂查询问题
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- 法律科技挑战与解决方案
- RAG技术局限性
- 无法处理隐性信息
- 依赖文件级人工核查
- Harvey合成数据集
- 100M+令牌规模
- 250+案件覆盖
金句 / Highlights
值得收藏与分享的关键句。
RAG无法处理'哪些并购交易未完成'这类需要文件级核查的问题
合成律所包含250+案件、46个客户、约10k文件
需人工逐文件检查才能确定未完成交易，自动化检索失效
Latent.Space on X: "The types of hard problems @EngramLab works on ft. co-founder @dan_biderman: "Clients do financing, mergers, acquisitions and things like take loans and do deals. And there's many queries that agents might run into which are these kinds of ambient, hard questions that are not https://t.co/aSRnGCZpeV" / X
@latentspacepod
The types of hard problems
@
works on ft. co-founder
dan_biderman
: "Clients do financing, mergers, acquisitions and things like take loans and do deals. And there's many queries that agents might run into which are these kinds of ambient, hard questions that are not easily searchable with RAG. For example, if you want to ask, which M&A deals haven't we completed this year? To actually solve this problem, you have to go client matter by client matter [and] read all the files. You can't read in any place that it was not completed."
$
00:00
/$
Harvey
@harvey
Aug 7
We're open sourcing a 100M+ token synthetic law firm we built with
. The firm contains work product from 250+ synthetic matters across 46 clients, spanning ~10k files. We built this environment to evaluate an agents' ability to search and understand a firm's past
Show more
8:05 PM · Aug 7, 2026
8.6K
Views
2
3
11
8