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

We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

arxiv.org

Post reply on HN
Print view View original

21–30 of 129 posts

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#21

Post by krageon »

Levitz wrote: post #16

I'm not sure what to think of this, on first impression I don't like it, but maybe I have a misguided impression on how this works. Does ChatGPT properly handle western social customs? I'd say yes, and I presume that's because it has a truckload of data involving such customs and even some that explicitly talks about those customs. People do stuff, it gets recorded, then into the LLM. In this case though we are talki…

It doesn't do normal what I would consider human politeness. It's all that really slimy salesman stuff. Even when you tell it to be more normal, casual or you give it an example (or to not dress it up at all) it ends up sounding like it thinks it's a few social classes above you.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#22

Post by agobineau »

It may be quite dangerous if we train LLMs on Taarof and Ketman... especially considering... what may arise. The masterful art of deception, surpassed perhaps only by the russianes

Arthur de Gobineau, Trois ans en Asie (3 years in asia) 1859:

“There is in Persia a word of which Europeans have no idea, and of which it is difficult even to give them a translation: this word is ketmân. It means the dissimulation of one’s thoughts, the concealment of one’s opinions, the careful hiding of what one truly believes or feels.

It is not considered a shame, still less a crime; it is, on the contrary, a virtue, a duty, and a necessity, imposed on everyone by the conditions of life. To practise ketmân is not merely permitted, it is commanded.

It consists in never allowing oneself to appear as one is, but in always showing oneself otherwise; it is the art of presenting to each person the aspect that will please him most, of adopting his ideas, his tastes, his language, while inwardly remaining quite different.

This perpetual exercise of disguise is carried out with a marvellous ease, and with a kind of pleasure in tricking others, which the Persians feel very keenly. They take delight in this ingenious hypocrisy; it is a game, a triumph of subtlety, in which the winner is the one who has best succeeded in hiding the truth.”

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#23

Post by philipp-gayret »

vidarh wrote: post #11
quotemstr wrote: post #10

> Native Persian speakers establish the human ceiling. Native speakers achieved an average accuracy of 81.8% on taarof-expected scenarios, demonstrating high but not perfect agreement. This establishes an appropriate ceiling for model performance and further validates our annotation approach I'm surprised human benchmark is that low. The canonical example of taarof, one I've seen elsewhere, is of a taxi driver insist…

> As an aside, there are elements of this sort of thing in Bay Area tech culture too. The more general case of misaligned strength of a statement is widespread in other cultures as well. E.g. I'm Norwegian, and it's not unusuals for Norwegians to use similarly soft language, though it's by no means universal. A statement like "perhaps it would be worth thinking about doing X?" will often mean "do X" or "do X right no…

> I live in the UK now, and my impression is that the same is true here but to a much lesser extent

I worked for a client once who had units in NL and BE, and a UK supplier. We had a short meeting once, it went like so:

> Architect(BE): I have an idea, let's do X!

> Developers(BE): OK boss!

> Developers(NL): Terrible idea. No way we're doing X. Let's do Y!

> Supplier(UK): Well X is interesting. None of our customers do X. But, it is possible!

BE thought X was a good idea, developers questioned it but an architect outranks them. NL thought they decided to do Y, and work on it will start the moment the meeting ends. UK thought they were very very clear not to ever do X.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#24

Post by kleiba »

agobineau wrote: post #22

It may be quite dangerous if we train LLMs on Taarof and Ketman... especially considering... what may arise. The masterful art of deception, surpassed perhaps only by the russianes Arthur de Gobineau, Trois ans en Asie (3 years in asia) 1859: “There is in Persia a word of which Europeans have no idea, and of which it is difficult even to give them a translation: this word is ketmân. It means the dissimulation of one’…

Sounds terrible.

But in all fairness, it's not like pretending isn't part of everyday Western culture too.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#25

Post by foobarian »

WJW wrote: post #7
LargoLasskhyfv wrote: post #6

I'll stubbornly resist, and consider this a form of unnecessary protocol overhead, leading to even more shmancy sycophancy, which I do not fancy!

That's kind of the point of politeness rituals in the first place, isn't it? To see who can be bothered to spend some extra effort to fit in and who doesn't care enough about the tribe to make the effort.

So... human proof of work? Wonder if we could start a new politeness trend by asking our tribespeople to solve short hashes

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#26

Post by cjauvin »

WJW wrote: post #4

Seems legit. There can't be all that much spoken Iranian in the training set(s) of these models, so it makes sense they don't know how to do it.

I've been using ChatGPT to learn Persian (as a third language) for more than a year now (along with a heavy use of Anki), and it's incredibly useful and surprisingly good, for about everything: romanization, OCR from screenshots, deep explanations of complex and subtle stuff, etc.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#27

Post by jemfinch »

agobineau wrote: post #22

It may be quite dangerous if we train LLMs on Taarof and Ketman... especially considering... what may arise. The masterful art of deception, surpassed perhaps only by the russianes Arthur de Gobineau, Trois ans en Asie (3 years in asia) 1859: “There is in Persia a word of which Europeans have no idea, and of which it is difficult even to give them a translation: this word is ketmân. It means the dissimulation of one’…

This sounds remarkably similar to the (western) Catholic theological concept of "mental reservation" (https://en.wikipedia.org/wiki/Mental_reservation).

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#28

Post by yk »

agobineau wrote: post #22

It may be quite dangerous if we train LLMs on Taarof and Ketman... especially considering... what may arise. The masterful art of deception, surpassed perhaps only by the russianes Arthur de Gobineau, Trois ans en Asie (3 years in asia) 1859: “There is in Persia a word of which Europeans have no idea, and of which it is difficult even to give them a translation: this word is ketmân. It means the dissimulation of one’…

Pretty sure bullshitting is pretty universal. In particular the pattern were I, the mighty expert, insist that only I, the mighty expert, can decode the meaning of those deceptive others, and therefore you, the gullible rube, has to give me all your money so that I, the mighty expert, can keep you, the gullible rube, save from those deceptive foreigners.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#29

Post by vidarh »

itopaloglu83 wrote: post #20
vidarh wrote: post #11

Earlier quoted context omitted.

> As an aside, there are elements of this sort of thing in Bay Area tech culture too. The more general case of misaligned strength of a statement is widespread in other cultures as well. E.g. I'm Norwegian, and it's not unusuals for Norwegians to use similarly soft language, though it's by no means universal. A statement like "perhaps it would be worth thinking about doing X?" will often mean "do X" or "do X right no…

Okay, here’s what I’m wondering: How do you urge people to do discoveries or try things out when you’re reviewing something? e.g. Do you think it would be better if we used a queue system here? Oh, no, I can try it but I had issues with blah blah etc.

One way would be to ask for an update before we make a decision. By making an explicit statement that a decision will be taken in the future you're making it clear that this wasn't the decision.

Another would be to be explicit about asking for them to conduct an experiment or test, as those would unambiguously not be intended to be a final solution.

But you might then well find that the request to carry out an experiment to do X will sound equally nebulous. But at least it's clear you're not being told it's a decision to do X.

Re: We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

#30

Post by vidarh »

philipp-gayret wrote: post #23
vidarh wrote: post #11

Earlier quoted context omitted.

> As an aside, there are elements of this sort of thing in Bay Area tech culture too. The more general case of misaligned strength of a statement is widespread in other cultures as well. E.g. I'm Norwegian, and it's not unusuals for Norwegians to use similarly soft language, though it's by no means universal. A statement like "perhaps it would be worth thinking about doing X?" will often mean "do X" or "do X right no…

> I live in the UK now, and my impression is that the same is true here but to a much lesser extent I worked for a client once who had units in NL and BE, and a UK supplier. We had a short meeting once, it went like so: > Architect(BE): I have an idea, let's do X! > Developers(BE): OK boss! > Developers(NL): Terrible idea. No way we're doing X. Let's do Y! > Supplier(UK): Well X is interesting. None of our customers…

As if there weren't good enough reasons to agree and circulate meeting outcomes, these kinds of things make them invaluable...
Post reply on HN