Comment by mfrye0
7 months ago
Yes, none of the top LLMs can do entity resolution well yet. I constantly see them conflate entities with similar names - they'll confidently cite 3 sources about what appears to be one company, but the sources are actually about 3 different businesses with similar names.
The fundamental issue is that LLMs don't have a concept of canonical entity identity. They pattern match on text similarity rather than understanding that "Apple Inc" and "Apple Records" are completely different entities. It gets even worse when you realize companies can legally have identical names in the same country - text matching becomes completely unreliable.
Without proper entity grounding, any business logic built on top becomes unreliable.
No comments yet
Contribute on Hacker News ↗