Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
1–10 of 110 posts
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#2Machine psychology is a field now:
https://arxiv.org/abs/2303.13988
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#3I’m totally against the anthropomorphization of LLMs. These are tools, not sentient beings. Treat them as such. Unlike a power tool, they don’t need respect because they cannot hurt you. LLMs trying to simulate human behavior is like the equivalent of skeuomorphism in UI design.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#4Sam Altman doesn't want you to say "please" to ChatGPT.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#5> Our study finds that the politeness of prompts can
significantly affect LLM performance. This phenomenon is thought to reflect human social behavior. The study notes that using impolite prompts
can result in the low performance of LLMs, which
may lead to increased bias, incorrect answers, or
refusal of answers. However, highly respectful
prompts do not always lead to better results. In
most conditions, moderate politeness is better, but
the standard of moderation varies by languages and
LLMs. In particular, models trained in a specific
language are susceptible to the politeness of that
language. This phenomenon suggests that cultural
background should be considered during the development and corpus collection of LLMs.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#6I’m still going to talk to it like a person because if I don’t then I’ll slowly start to talk to people like they’re LLMs and it’s going to sound rude.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#7Sam Altman doesn't want you to say "please" to ChatGPT. https://futurism.com/altman-please-thanks-chatgpt
That is not true; first he says it's "tens of millions of dollars well spent," followed by "you never know". I don't think he knows.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#8I’m totally against the anthropomorphization of LLMs. These are tools, not sentient beings. Treat them as such. Unlike a power tool, they don’t need respect because they cannot hurt you. LLMs trying to simulate human behavior is like the equivalent of skeuomorphism in UI design.
They’re also language tools, built on the ingestion and training of language and its tone, form and application. The way they work, by inferring responses based on the probabilistic best response to your language prompt, means the construction of your input in its tone, form and application will influence the quality of output.
It might offend you to show deference to a tool but ignoring the optimal way to use a tool on principle is foolish.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#9Note that this uses llms from 2023(chatgpt3.5-turbo, chatgpt4), and might not be relevant to newer models.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#10I’m totally against the anthropomorphization of LLMs. These are tools, not sentient beings. Treat them as such. Unlike a power tool, they don’t need respect because they cannot hurt you. LLMs trying to simulate human behavior is like the equivalent of skeuomorphism in UI design.
Because LLMs match your prompt to data scraped off the internet, it’s plausible that being polite results in your response coming from more civil conversations that have more useful data.