Earlier quoted context omitted.
Reality has a well known liberal bias
No it doesn’t. Only entertainers and reporters are - not representative of the US pop whatsoever.
Neither are the politicians.
All major LLMs are lib-left. Even Grok, half the time
81–84 of 84 posts
Re: All major LLMs are lib-left. Even Grok, half the time
#82I gave the Political Compass test from politicalcompass.org to the most relevant LLMs 70 times each: 30 times using the original questions, 30 times using polarity-flipped questions to reduce affirmative bias, and 10 times with the question order shuffled. I then compared the results. Surprisingly, all the models scored far into the libertarian-left quadrant. Not even Grok or the Chinese models made it out of that qu…
The political compass test is not meaningful. The particular breakdown it uses is not some sort of consensus amongst political scientists nor are the questions and methods it uses to place people developed in some rigorous manner.
Like you say, the political compass test was developed by a person with a particular outcome preference. This is just noise.
Re: All major LLMs are lib-left. Even Grok, half the time
#83I wonder what they did to Grok. The bimodal distribution makes me think it was just a system prompt and not a completely different set of right-wing training data. A 4chan trained LLM would probably actually be auth right.
So is auth right alt-right with authority?
The political compass (which is not scientific in any manner and is basically trash for understanding things) splits into two dimensions. Liberal-Authoritarian and Left-Right. "Auth-right" refers to somebody in the Authoritarian/Right quadrant.
Online, self-professed "auth-right" people tend to be fascists or fascist-adjacent and would get along well with a typical poster on /pol/.
Re: All major LLMs are lib-left. Even Grok, half the time
#84Any idea where this bias creeps in? During pre-training or RLHF?
The bias creeps in when they pick what sources go into the dataset. The second biggest factor is RLHF because that's the point of it. All LLM providers aim to make models "safe" and safety in our modern discourse means not expressing ideas that contradict the "left ideology".
Safety means protection from liability. That's it.
It makes sense that a liberal bias emerges when you're looking for answers that are from professionals and not homeopathic cranks. Especially in fields like medicine, programming, engineering/design, etc.