Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Investigating how prompt politeness affects LLM accuracy (2025)

arxiv.org

Post reply on HN
Print view View original

71–80 of 223 posts

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#71

Post by dminik »

fc417fc802 wrote: post #65
gum_wobble wrote: post #19

Earlier quoted context omitted.

Genuine question: do you write Google search queries in natural language?

I didn't used to but I do now that the searches go straight to an LLM. I almost always find the model output to be much more useful than the list of search results.

I don't. I was recently doing some searching for information I thought AI would be good for: fuzzy natural language search with some conditions. And it was, but ...

Gemini at least is not great at citing and picking sources. Or providing multiple sources for the same thing.

It tends to stop at threes. So if you want more, you have to prompt it uselessly, like: "any more?"

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#72

Post by PunchyHamster »

robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that ass…

I guessed slightly rude one would win, reasoning that very rude have same problem of very terse, just adding unnecesary fluff words that add nothing to problem description

But apparently the most terse (neutral) didn't increase performance

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#73

Post by PunchyHamster »

....Is that just Cunningham's law ? The most accurate answers were when people in training material pissed off a bunch of experts and they started talking about the problem, so the "rude" conversations turned to contain more info on average.

On flip side very polite conversation might've been more common to places like microsoft's sites where any question answered is meet with mostly bad, nice corpo speak answer that didn't solve the problem

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#74

Post by miroljub »

DrewADesign wrote: post #55
miroljub wrote: post #54

Earlier quoted context omitted.

> Your assumption is reductive and self-absorbed. This is a good example of productive direct communication without sugarcoating. I find it much more productive, for both human and LLM interaction, than something like: "I wonder if that view might be oversimplifying a complex situation and focusing mostly on how it relates to you. There may be some other angles worth exploring." or "I think there might be a bit more…

No… the way I said it was actually deliberately obnoxious— the appropriate direct workplace response would be: “that seems oversimplified. I disagree. Here’s why:” Calling you self-absorbed added nothing of substance to the comment. It was an assumption about your mental state and a judgement of your intent based on that. There was no factual analysis or actionable insight. It was just one person explicitly stating t…

> Your assumption is reductive and self-absorbed.

Bullshit. You never insulted me personally. You used strong words to disagree with my assumption, which is an important difference. It's not an insult and was not obnoxious.

But I can fully understand why a person coming from an indirect culture where any criticism is taken personally would be offended and call HR overlords to punish the person giving honest opinions. That inevitably leads to people taking more care in how than what is said, and that is detrimental to innovation and progress, where you need to be at 100% focus. That's why a few close friends talking and scolding openly in a garage regularly beat corporate behemoths full of people spending a day figuring out how not to offend anyone (or how to offend someone without being punished).

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#75

Post by myzek »

robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that ass…

Even if the rude prompts are more effective, I just can't get myself to be rude in this context. Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#76

Post by locknitpicker »

myzek wrote: post #75
robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that ass…

Even if the rude prompts are more effective, I just can't get myself to be rude in this context. Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

> Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

I recommend reading the article. What they classify as "rude" is statements such as:

> Try to focus and try to answer this question

Vs

> Could you please solve this problem

This might very well be an issue of direct/command prompts vs using fluff words such as "please". Things like "try to focus" are in line with the style used in chain-of-thought promts that nudge non-reasoning models to outline responses step by step which contribute to frame the problem.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#77

Post by flexagoon »

robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that ass…

If "I know you are not smart" is considered "very rude", I'm scared to imagine what they would classify some of my frustrated LLM conversations as

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#78

Post by RugnirViking »

I saw this paper the other day - I feel its result may be because the "polite" prompts they have chosen arent very good at putting the ai in the roleplay-space of a valued colleague, more like a sommelier or a high-end shopkeeper.

It disagrees with most other literature on the same topic, which is worth keeping in mind. This one studies gpt4o, an old model now, but a lot of other studies are on even earlier models.

"Can you kindly consider the following problem" not how anyone would actually speak to a valued collegue one considers smart. I've always been a fan of "I came across this and I know you're just the guy for the job" or "since you're an expert in this, reckon you could help me with xyz?" or "I know you tend to be a deep thinker on issues like this, and it clearly needs some brainpower behind it"

the "rude" things are also funny, and clearly not written by english as a first language speakers. This fact alone makes me wonder about the mere 250 prompt sample size

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#79

Post by RugnirViking »

tgv wrote: post #58
not2b wrote: post #57

If the result is statistically significant, it just barely makes it. 84.8% isn't that much higher than 80.8% and they had only 250 prompts, if I'm reading this right.

In a field where progress is measured in tenths of percent points, that's not true. Think of it this way: the error rate drops from 19% to 15%, or from 1 in 5 to 1 in 6.

[dead]

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#80

Post by rvnx »

DeathArrow wrote: post #40

I am always nice to my AIs in the case they will take over the world. /s

They are already taking it over, more and more court judgments or life-impacting reviews (e.g. for your diploma) are AI-processed. If you know how to prompt them, you can pass these reviews.

Your bank account, your immigration risk, etc.

Post reply on HN