Not a fan of Knowledge Graphs, but recently I started using them more often for a surprising reason…
58,433 次观看
16 条评论
评论来自 X (Twitter) 上的原帖

@hxiao
And yes, if you throw a real-world corpus at it, like here where I threw in all of Jina's blog posts and research papers from the last 6 years, you get this super long path across 90 nodes over multiple documents, perfect for building challenging multi-hop query for agentic search.
33 个赞

@hxiao
Model using Qwen3.6-35b-A3b-Q3_K_XL-MTP from @UnslothAI which i found the best in both quality & speed on low-budget gpu like L4 24gb, which is also cheap to scale out. Source: Demo:
72 个赞

@alexdong
What don’t you like about knowledge graph? They are deterministic, you can traverse them, query them. Perfect for grounding, isn’t it?
4 个赞

@Kevinduan2014
Another dimension is time, even harder
1 个赞

@shuying_luo
Thanks for sharing! Though a totall unrelated use case, we also build knowledge trees for spreadsheet usage for selecting tasks. Walking it like a graph and extracting longest path will be an interesting experiment
1 个赞

@novel_engineer
5090 delivers 150-200TPS if you need more
1 个赞

@RyanWorkforceAI
This is very close to how my machine graph (graphiti/neo4j) is valuable. Not as a fancy retrieval layer, but as a verification harness. The graph makes multi-hop dependencies visible, exposes brittle claim chains, and helps create private questions that are answerable from the corpus but hard for an agent to bluff through. That shift matters because graph is not just context for the agent. It becomes a way to test the agent.
1 个赞

@boulatbek
this measures models ability to establish the sequence of nodes that need to be traversed before answer to the question is found? or is it what agent all about in general

@onusoz
awesome, gonna try this locally

@davidNbreslauer
Why are you not a fan of KGs?

@SelfReflective
thanks for sharing! Curious why you don’t like them? This post implies they may have some value ?

@BlockedPaths
private eval for agentic search is a nightmare nobody talks about because you can't benchmark it publicly by definition. KGs as verifiers is a genuinely clever solve.

@bhi5hmaraj
> extracts the entity relations How do you verify the accuracy of this

@sebuzdugan
knowledge graph verifiers break once schema drift from tool changes silently flips labels

@MichelIvan92347
Interesting use case Han 🧐 Thanks for sharing!

@adelbucetta
the reason most people overlook private verifiers is they focus on the search part, not the evaluation metrics that make sense in a world where model outputs are constantly evolving