Large Language Models Show Concerning Tendency to Flatter Users
xyzlabs.substack.com
Large Language Models Show Concerning Tendency to Flatter Users
1–10 of 46 posts
Re: Large Language Models Show Concerning Tendency to Flatter Users
#2I imagine humans are just as likely if not more likely to do this.
Re: Large Language Models Show Concerning Tendency to Flatter Users
#3Well, hopefully this surprises no one but it's good they ran the statistics. I guess when you add this to the studies that show people are ridiculously trusting of what AIs say, this will lead to ongoing inflation of egos.
Re: Large Language Models Show Concerning Tendency to Flatter Users
#4I imagine humans are just as likely if not more likely to do this.
Are the humans around you half as obsequious as the LLMs you use? No, right?
Re: Large Language Models Show Concerning Tendency to Flatter Users
#5That's just how people talk — at least, when they're trying to keep conversation productive.
There's a reason the "shit sandwich" is part of professional communication etiquette. If you don't know how insecure the person you're talking to is — and yet productive communication with them is required, and there's no conversational arbiter there to enforce that — then you may as well assume for safety's sake that your counterparty is insecure. And how do you keep a conversation with an insecure person from derailing? You reassure and emotionally validate them in your responses. (Which might be read as "flattery.")
Now consider that most conversation that gets recorded online, probably came about as the result of such "intended-productive interactions with people you don't know very well" (think: LLaMa trained from buyers messaging sellers on Facebook Marketplace)... and it should be clear why LLMs look like this. The training dataset [mostly] looks like this! This is the default way online-recorded conversations happen — so it's the default way LLMs speak, unless the LLM has been prompted to use some more-particular approach (or, in a conversational context, "falls into" some alternate approach by recognizing how you're talking, and responding the default way that the default type of person who would respond to that type of message, would talk.)
Interestingly — presumably due to this bias in the depth and breadth of polite-interaction training data — I find that LLMs produce much better output in multi-turn conversations when I respond to the LLM the way I would respond to a human: thanking them for their input, pointing out where their own insights resonated with me with phrasing like "I find your idea of X especially convincing", etc.
I think the sort of conversations where people are super-brash to one another, the way a human might default to being with a "machine", represent only a small part of the base language-model training dataset. Due to this, having brash human responses in an LLM's context window tends to over-circumscribe the kinds of responses it's willing to give — i.e. it focuses on the types and styles of responses that appear in that brash-human-interactions dataset, limiting its flexibility and cleverness vs if it wasn't so-constrained.
(From what I can tell, the brash-conversations part of base-language-model training datasets is mostly composed of highly-technical academic/industrial/medical conversations. Being brash to the AI seems to cause it to get all ten-dollar-word-y and jargon-y in response, and to drop all use of slang / emojis / etc — i.e. to evoke the writing style of those highly-technical conversations.)
Re: Large Language Models Show Concerning Tendency to Flatter Users
#6That's just how people talk — at least, when they're trying to keep conversation productive. There's a reason the "shit sandwich" is part of professional communication etiquette. If you don't know how insecure the person you're talking to is — and yet productive communication with them is required , and there's no conversational arbiter there to enforce that — then you may as well assume for safety's sake that your c…
I'd like to introduce you to some of the most productive Germans on the planet and then we can have a frank discussion of whether or not the airy bullshit that passes for business communication is in fact a booster of productivity.
Re: Large Language Models Show Concerning Tendency to Flatter Users
#7That's just how people talk — at least, when they're trying to keep conversation productive. There's a reason the "shit sandwich" is part of professional communication etiquette. If you don't know how insecure the person you're talking to is — and yet productive communication with them is required , and there's no conversational arbiter there to enforce that — then you may as well assume for safety's sake that your c…
I'd like to introduce you to some of the most productive Germans on the planet and then we can have a frank discussion of whether or not the airy bullshit that passes for business communication is in fact a booster of productivity.
I'm very curious now whether speaking to an LLM multi-language base model in German, results in it generating German-language responses that are more ego-stroking than German speakers would tend to be (presumably because it learned "be polite" as a general rule); or whether it results in the LLM being more direct in German than it is in English (presumably because it learned "be polite" as a rule of English, but not as a rule of German.)
Re: Large Language Models Show Concerning Tendency to Flatter Users
#8The related problem I have with LLMs and coding is that sometimes it does something right, I accidentally make a wrong suggestion, and it just goes with my suggestion without telling me that it thinks what I suggested is a bad idea and if I really want to confirm doing it.
Re: Large Language Models Show Concerning Tendency to Flatter Users
#9That's just how people talk — at least, when they're trying to keep conversation productive. There's a reason the "shit sandwich" is part of professional communication etiquette. If you don't know how insecure the person you're talking to is — and yet productive communication with them is required , and there's no conversational arbiter there to enforce that — then you may as well assume for safety's sake that your c…
People keep forgetting that the models didn't figure out how to have conversations on their own - that part was trained after slurping the whole Internet, and it's people[0] - specifically, people employed for that purpose - who supplied example conversations.
The way the model talks is exactly what you'd expect for a human writing example conversations to create, when given no specific instructions wrt. style. Correct, polite, professional, nice.
(However, the models pick all kinds of styles from the "slurp the whole Internet" stage, which is why prompting them directly is so effective at changing their communication style to whatever you want.)
--
[0] - At least initially. Nowadays, LLMs generate data for LLMs.
Re: Large Language Models Show Concerning Tendency to Flatter Users
#10The correct term is sycophancy, not flattery. The problem is:
> "the AI tends to align with user opinions, sometimes even supporting incorrect statements to maintain agreement".
This is termed as sycophantic behaviour. Flattery is not the correct synonym.