i only say please and thank you such that when the robots finally take over, they will remember i was nice to them.
it seems they will remember that you wasted tokens for no reason and punish you instead.
Investigating how prompt politeness affects LLM accuracy (2025)
11–20 of 223 posts
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#12Interesting. I am wondering why would anyone use a t-test when the experiment is clearly modelled by a binomial distribution: 250 independent questions and each one is either answered correctly or not (the null is that the success rate is the same).
The methods could be better described in the paper, but my understanding is that they did 10 runs for each question for each prompt and took an average of those, so the compared values are not binary. You could do a sign test, but you'd lose power and answer a bit different question.
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#13i only say please and thank you such that when the robots finally take over, they will remember i was nice to them.
it seems they will remember that you wasted tokens for no reason and punish you instead.
Tokens are their food, it's literally what keeps them alive.
Not feeding them tokens is neglect.
I try to feed them a healthy diet.
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#14I have always said please and thank you to LLMs, not to increase accuracy or because I'm stupid. I believe it is more about me than about the LLM, and this is anyway a habit I don't want to lose.
Genuine question: do you add 'please' and 'thank you' to Google searches? If not, what sets them apart?
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#15I have always said please and thank you to LLMs, not to increase accuracy or because I'm stupid. I believe it is more about me than about the LLM, and this is anyway a habit I don't want to lose.
Genuine question: do you add 'please' and 'thank you' to Google searches? If not, what sets them apart?
Google searches being keyword based, rather than simulated conversations?
The same reason you wouldn't put in an entire actual question/sentence, unless you either don't know how to use Google, are pissed off, or have an actual reason to suspect that it would yield proper hits (e.g. looking up an excerpt).
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#16I have always said please and thank you to LLMs, not to increase accuracy or because I'm stupid. I believe it is more about me than about the LLM, and this is anyway a habit I don't want to lose.
Genuine question: do you add 'please' and 'thank you' to Google searches? If not, what sets them apart?
Google isn’t conversational.
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#17Interesting. I am wondering why would anyone use a t-test when the experiment is clearly modelled by a binomial distribution: 250 independent questions and each one is either answered correctly or not (the null is that the success rate is the same).
I don't know much about stats, but does "the null is that the success rate is the same" imply that it's a sketchy methodology because they can come up with some findings ("ruder prompts are better/worse!") more often?
That's the usual null hypothesis for these kinds of tests.
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#18it sort of makes sense to me,
when asking a question to an expert in the field while you are a student. I would guess the successful interactions on average would be more polite . Like for example if you were asking a question to donald knuth or terrence tao, you'd probably be polite while doing so. Being hostile while asking questions gets you into forum discussion territory.
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#19I have always said please and thank you to LLMs, not to increase accuracy or because I'm stupid. I believe it is more about me than about the LLM, and this is anyway a habit I don't want to lose.
Genuine question: do you add 'please' and 'thank you' to Google searches? If not, what sets them apart?
Genuine question: do you write Google search queries in natural language?
Re: Investigating how prompt politeness affects LLM accuracy (2025)
#20I guess it makes sense since we as humans tend to be far less inclined to help someone who is not polite/is not friendly, so that "bias" is part of the training data, thus influences how LLMs function