ijyliu / anlp23-project

An empirical study of the costs and practicalities of prompt engineering techniques on standard and novel benchmarks
0 stars 0 forks source link

checking ballparking of llms #60

Open ijyliu opened 9 months ago

ijyliu commented 9 months ago

how close are wrong answers?

in the real world, are they wrong enough to cause problems?

ijyliu commented 9 months ago

would require reading math answers as numbers