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

81–90 of 223 posts

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

#81

Post by Asraelite »

DrewADesign wrote: post #50
miroljub wrote: post #45

Earlier quoted context omitted.

> 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 associated rudeness with poorer outcomes, suggesting that newer LLMs may respond differently to tonal variation. The expectation is naive. Even when communicating with humans, you get a better outcom…

Your assumption is reductive and self-absorbed. Obnoxious people have repeatedly shown to be detrimental to productivity at the organizational level. Some people are simulated by confrontation. Most people are clam up. Confrontational people think it’s more efficient because other people frequently just drop the topic and let them win, or avoid discussing things with them altogether. The obnoxious person might think…

You are conflating obnoxiousness with directness.

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

#83

Post by swingboy »

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…

“Hey gofer, figure this out” is my new prompt opener.

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

#84

Post by narag »

TimCTRL wrote: post #9

i only say please and thank you such that when the robots finally take over, they will remember i was nice to them.

I do that for a different reason: my self image. Fear of retribution and performance, not so much. Should I behave like a rude person to achieve a little better answers? Fuck that shit!

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

#85

Post by danparsonson »

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.

Statistical significance is about whether an effect can reliably be said to have been measured at all; it's not about whether or not the effect itself would be significant in the sense of moving some other needle.

The ~5% improvement reported here might just be an artefact of the data collection or random variation, rather than a consistent repeatable change.

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

#86

Post by sovareq »

nottorp wrote: post #64
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…

Hmm by the abstract and the question list they didn't measure terse fluff-less prompts?

[flagged]

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

#88

Post by kstenerud »

My first guess would be that polite requests cause some agents to trust their initial approach to the problem more, as the caller has indicated that the agent is more capable, and agents tend to take the implications of what you say at face value since they are trained to be accommodating.

It would be interesting to see this experiment run using prompts leading with "You'll probably get this wrong, but I'm asking anyway in case you get it right: ..."

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

#89

Post by bcjdjsndon »

locknitpicker wrote: post #76
myzek wrote: post #75

Earlier quoted context omitted.

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 us…

Isn't all this massively dependent on what they trained the llm on?

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

#90

Post by bcjdjsndon »

Asraelite wrote: post #81
DrewADesign wrote: post #50

Earlier quoted context omitted.

Your assumption is reductive and self-absorbed. Obnoxious people have repeatedly shown to be detrimental to productivity at the organizational level. Some people are simulated by confrontation. Most people are clam up. Confrontational people think it’s more efficient because other people frequently just drop the topic and let them win, or avoid discussing things with them altogether. The obnoxious person might think…

You are conflating obnoxiousness with directness.

Rudeness is completely arbitrary and you have to figure it what exactly is rude by, basically, upsetting humans and avoiding whatever caused the upset in the future.

People who either can't or don't want to do that say they're "direct" or "honest" or "logical" but there's another word for it, begins with A

Post reply on HN