Re:Teach your LLM to answer with facts, not fiction
by janalsncm on Monday July 24, 2023 @03:41AM
(#36844283)
The “exercise for the reader” in this case is the entire point of the metric. If it were possible to do at scale it could be incorporated into existing models right now.
Second, it isn’t even necessarily better to have fewer lies if those few lies are more subtle. Plenty of propaganda works by twisting facts and using misleading statements. Perhaps the worst offenders won’t even have any outright falsehoods at all.
Re:Teach your LLM to answer with facts, not fiction
by ddmma on Monday July 24, 2023 @06:06AM
(#36845376)
that is very interesting input, thanks! Also split into sentences, similar to what sentiment analytics does would raise the level of complexity into the output metric.
Second, it isn’t even necessarily better to have fewer lies if those few lies are more subtle. Plenty of propaganda works by twisting facts and using misleading statements. Perhaps the worst offenders won’t even have any outright falsehoods at all.