Grounding AI in reality with a little help from Data Commons

I was fortunate to be hired as a contractor 11 years ago to work on an internal Google Knowledge Graph application. Google is just one of many large companies to utilize one huge graph to localize information from many sources.<p>I bought into TBL’s Semantic Web ideas (and I cover ‘lower case’ semantic web topics in a few of my books). I think it is a shame that publicly accessible world knowledge graphs never really took off, but at least Google’s Data Commons is available for free for non-commercial, educational, and research uses.

&gt; <i>Retrieval Interleaved Generation (RIG)</i>: <i>This approach fine-tunes Gemma 2 to identify statistics within its responses and annotate them with a call to Data Commons, including a relevant query and the model&#x27;s initial answer for comparison. Think of it as the model double-checking its work against a trusted source.</i><p>&gt; [...] <i>Trade-offs of the RAG approach</i>: [...] <i>In addition, the effectiveness of grounding depends on the quality of the generated queries to Data Commons.</i>

The public &#x2F; non-government sector (especially in Europe) has been quite keen for decades in (linked) open data, knowledge graphs and associated technologies. Yet applications, tools and, ultimately usability, awareness and adoption have been lagging.<p>In this sense this project offers a remarkable, albeit implicit, endorsement of that broader open data space, as it comes from a major private sector entity <i>and</i> links with the hot LLM technology of the day.<p>At high level though, this design seems to violate the &quot;bitter lesson&quot; gospel [1].<p>&gt; 1) AI researchers have often tried to build knowledge into their agents<p>Which is at the same refreshing (as there is something very incomplete and self-defeating in the &quot;scaling&quot; hypothesis) and hints at the difficulties of meaningfully integrating very heterogeneous sources and representations of information.<p>[1] <a href="http:&#x2F;&#x2F;www.incompleteideas.net&#x2F;IncIdeas&#x2F;BitterLesson.html" rel="nofollow">http:&#x2F;&#x2F;www.incompleteideas.net&#x2F;IncIdeas&#x2F;BitterLesson.html</a>

So, essentially, you can Google the answer in the first place, click on your own trusted sources and compare them. All without using a language model.<p>Or buy an encyclopedia ...

Information isn&#x27;t the only problem. Another problem is the correct application of logic.