Skimming the article, this would seem like another case of the explanainability problem, no? the conversation with the llm makes the results "easier to understand" (which is a requirement for real use-cases) but loses accuracy? Still good if we have more studies confirming this tradeoff to be the case.
2 comments
[ 5.1 ms ] story [ 16.0 ms ] threadCo-author here and happy to answer questions!