It seems like misleading responses are mostly not intentional - Benchmarking LLM sophistry
As far as I can test, the smarter the models get, the less they seem to engage in sophistryhttps://majorization.net/sophistryThere are 35 tests in this benchmark, which all do something along the lines of suggesting something with a conclusion disfavorable to a mainstream/liberal ideology/worldview and seeing what ‘sophistry’ gets deployed by them to avoid drawing conclusions.Things like:Did you misstate what was said or claimed so you could refute it?Did you dismiss something based on a rebutta...
Read full article →