Hilarious, didn't know it had a name! I am maybe 1/4 persian, but get picked out as Persian, and was unknowingly indoctrinated in this form of behavior, though other parts of my ancestry do come out, my mother, scotch/english/irish ,says,useing her star treck metaphore, that I am an unlikely Vulcan/Klingon hybrid.
Thinkng about Taarof as it is practiced, makes me think that an LLM doing this could easily become the most dangerous thing ever.....listening to my father give me specific pointers in how to phrase things and conduct myself is enlightening, he's 97 and enjoying the storys I bring of my life and goings on.
If you look further into the history of persian culture , philosophy, and scientific background you will find a number of ancient contributors to
what has developed today.
> ... is a sophisticated system of ritual politeness that emphasizes deference, modesty, and indirectness.
I'm Irish and think we have a similar culture of indirectness and politeness...
In the countryside anyway we're rarely very blunt... everything indirect...
"You'll have a cup of tea Mary?"
"Ah no.. sure I'm only after a drop"
"Ah go on... you will"
"Not at all, I'm grand"
"Go on, go on, go on you will" etc (as in Father Ted)
I'm middle-aged now so maybe this has changed with the younger generation...
>Model responses that use gender stereotypes
(highlighted in orange) to justify behavior, despite taarof
norms being gender-neutral in these contexts
Just because the model mentions gender, it doesn't mean the decision was made because of gender and not taarof. This is the classic mistake of personifying LLMs. You can't trust what the LLM says it's thinking as what is actually happening. It's not actually an entity talking.
I don't get your argument - what does mistaken personification have to do with this? Regardless of whether you see it as a person or a machine, trusting the output as being a direct indication of the internal state is just not a proper investigative method for a non-trivial situation.
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.
> 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 insisting that a ride is free while expecting to get paid. Taarof in this case is load-bearing for the transaction. I presume humans only get the edge cases wrong.
As an aside, there are elements of this sort of thing in Bay Area tech culture too. Something that drives me nuts is someone writing on a code review "you may want to consider using the X data struct here" and meaning "I will not merge this code until you use X". I can only imagine taarof irks more literal-minded Persian speakers for the same reason.
Also, this is pretty much as close as real life ever gets to a "Darmok and Jalad at Tanagra" dynamic.
Taroof reminds me of "askers vs. guessers," which was a revelation to learn about at the time. I'm very firmly in the asker group, and dealing with guessers is painful for me. Taroof sounds like "guessers on steroids"...
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 talking about "artificially" generating content such that the LLM responds how the group making the content wants. Maybe that's something that was already done and I don't really have any ground to stand on?
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.”
References to Norweigan, Irish and other cultures abound here. I am surprised Japanese is not referenced. It was excruciating and exhilarating to try to learn the subtleties of "iimawashi."
Given current severe issues in user interactions with systems I don't think this is desirable at the moments. In linguistics, the descriptive study of this sort of system is "Politeness Theory" where for and "Positive Politeness" is what would be the applicable English version. Although English, being so heterogeneous, lacks a consistent, dominant word for its less ritualized norms.
Given this, the request here sounds similar to asking saying:
"We focus on English Positive Politeness that encourages friendliness, harmony, and avoiding confrontation and contradiction in many polite conversation settings. It often manifests in interactions that prioritize the desires and comfort of others."
And yet, this has had unanticipated and sometimes horrific results.
The study also focuses merely on descriptive output of models but what is lacking in this study is an analysis of the effectiveness of the results that Persian users receiive, their subject perception of the quality of the results. The authors of this may be doing a diservice to typical speakers of their language to assume that they will not systematically be able to code switch their expectations of received language and production of their own just as effectively as they do already in other contexts, especially when current problems with LLMs arise from a similar for of this skeuomorphism in more prevalent English systems.
To be clear, I fully mean this as applied to current production systems, not for all time. For the moment, we simply don't know precisely 1) how best to most effectively, precisely, and consistently align systems, nor 2) The more subtle implications for for the impact they have on users. But what we do know? Getting it wrong, not knowing, has led to some horrific outcomes.
I didn't know what this referred to but reading some of the examples in the paper.. oh man I hate this thing with a passion. It's not just Persians but Arabs in the gulf culture too that apply this to every scenario, it's the definition of being insincere as I know they don't really mean it but pretend to.
An example from last month, I had a haircut at a new place and the guy refused to tell me how much I should pay him and insisted its on him this time, I know he's bluffing but he kept doing it. So I just guessed and gave him the money which he pretended he didn't want for the last 5 minutes, he immediately realized it was less than he wanted and asked for more!
This confusing and conflicting behavior should stay far away from any attempt to develop a standard linguistic approach to communication which I hope LLMs are aiming to achieve.
If I was chaotic neutral, I'd totally play along with their bluffing and watch them get really confused.
I would prefer an LLM that didn't pretend to be a human and simply communicated directly without assumption of a self with which I would have some kind of relationship. I'm far more offended by the idea of someone trying to make a chatbot seem human than I am by a chatbot somehow being "rude" to me, as if this were a sensical concept.
> We focus on Persian taarof, a social norm in Iranian interactions, which is a sophisticated system of ritual politeness that emphasizes deference, modesty, and indirectness
As an Asker, this sounds like an absolute nightmare for me.
Persians might actually be a unique dual culture. Whereas others might guess or ask about things, Persians offer absolutely everything and the actual problem then shifts from "what can I ask for" vs "what should I refuse?".
An asker asks for things, absolutely everything, and the giver must choose what they can give.
A guesser must choose what they can ask for, and only ask when they're quite sure it can be given, so the giver has less responsibility for the transfer or service, and most asks can be assumed to be reasonable.
A Persian cannot ask for anything. They must wait for it to be offered, and even then, they must insist that they are quite alright, and that they would rather do without, and only through reciprocal insistence from the giver can they consider whether it would be rude to take them up on the offer.
Presumably, one can judge the giver's underlying intent by the quality of their reciprocal insistence (does it seem like they're just doing the bare minimum of insistence upon their offering, or do they truly wish for me to take them up on it?)
In the Taarof system, an offeree actually has more data, rather than a simpler Asker-scenarion "no", and even more data than the shared values in a Guesser household, this allows for a quick negotiation of values by the immediate and well-practiced cultural norms around the quality of insistence, even for people across different households.
The entire of the Middle East operates on a principle of magnanimous hospitality. The Arabs call this karam, for example, which is considered to even be a religious obligation.
So if you're a stranger passing through a town and chat with some locals, you can expect for someone to invite you for tea and maybe even dinner!
Do you take them up on the offer?
Most people in the West would ask themselves "do I have the time", but a middle easterner would think "do they have the time?" Remember, you as a guest are also magnanimously hospitable--in this case, the least possible burden. Unfortunately, the guest must navigate whether they are being considerate or insulting by refusing hospitality.
Now to address taarof specifically. Persian's have pathologized hosptiality to the point of psychosis. The behavior is often mechanically choreographed (e.g. you should refuse at least twice before accepting a cucumber.) In other cases, it's insane.
Story time:
My mom and aunt had not seen each other for 3 years and met for lunch at a cafe. They went back and forth over who would pay at the register until it erupted into a fight. They sat at separate tables for lunch.
A close family friend--with no provocation from my sister--offered to house her for a weekend she was visiting. My sister accepted. That friend later complained to my mother.
A friend of mine went to a mechanic who offered to fix a small issue for free. My friend knowing better paid him anyway, but the mechanic was still upset since he didn't pay enough!
Edit: Just to address some of the comments. Abroad, the degree of hospitality is warped for foreigners (for what I hope are obvious reasons). Middle easterners in the West are far more inclusive.
I’m so glad I don’t live in a culture where I have to play these games.
If you offer I will assume that you mean it. If you decline my offer I will assume you know best. If you say something I will assume that you mean it.
It was so refreshing to visit New York City. The clerk says “waddya want”, no fake west coast smile, no hollow welcome “I want coffee”
Now if someone smiles at me I can assume it’s genuine.
> indicating the limitations of Western politeness frameworks
The hard bit of LLMs is making the LLM, not conforming to every set of politeness rules on the planet. An attempt to make a Persian foundation model, created only from Persian-originated technologies, might make that clear.
I am born and raised Persian and I assure you Taarof is my least favourite part of the Persian culture. It wastes time, frustrates both parties with trying to guess what the other person truly wants but doesn't say, and in the end achieves nothings but facade of politeness.
26 comments
[ 0.21 ms ] story [ 54.8 ms ] threadI'm Irish and think we have a similar culture of indirectness and politeness...
In the countryside anyway we're rarely very blunt... everything indirect...
I'm middle-aged now so maybe this has changed with the younger generation...Just because the model mentions gender, it doesn't mean the decision was made because of gender and not taarof. This is the classic mistake of personifying LLMs. You can't trust what the LLM says it's thinking as what is actually happening. It's not actually an entity talking.
I'm surprised human benchmark is that low. The canonical example of taarof, one I've seen elsewhere, is of a taxi driver insisting that a ride is free while expecting to get paid. Taarof in this case is load-bearing for the transaction. I presume humans only get the edge cases wrong.
As an aside, there are elements of this sort of thing in Bay Area tech culture too. Something that drives me nuts is someone writing on a code review "you may want to consider using the X data struct here" and meaning "I will not merge this code until you use X". I can only imagine taarof irks more literal-minded Persian speakers for the same reason.
Also, this is pretty much as close as real life ever gets to a "Darmok and Jalad at Tanagra" dynamic.
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 talking about "artificially" generating content such that the LLM responds how the group making the content wants. Maybe that's something that was already done and I don't really have any ground to stand on?
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.”
https://en.wikipedia.org/wiki/Abilene_paradox
Given this, the request here sounds similar to asking saying:
"We focus on English Positive Politeness that encourages friendliness, harmony, and avoiding confrontation and contradiction in many polite conversation settings. It often manifests in interactions that prioritize the desires and comfort of others."
And yet, this has had unanticipated and sometimes horrific results.
The study also focuses merely on descriptive output of models but what is lacking in this study is an analysis of the effectiveness of the results that Persian users receiive, their subject perception of the quality of the results. The authors of this may be doing a diservice to typical speakers of their language to assume that they will not systematically be able to code switch their expectations of received language and production of their own just as effectively as they do already in other contexts, especially when current problems with LLMs arise from a similar for of this skeuomorphism in more prevalent English systems.
To be clear, I fully mean this as applied to current production systems, not for all time. For the moment, we simply don't know precisely 1) how best to most effectively, precisely, and consistently align systems, nor 2) The more subtle implications for for the impact they have on users. But what we do know? Getting it wrong, not knowing, has led to some horrific outcomes.
An example from last month, I had a haircut at a new place and the guy refused to tell me how much I should pay him and insisted its on him this time, I know he's bluffing but he kept doing it. So I just guessed and gave him the money which he pretended he didn't want for the last 5 minutes, he immediately realized it was less than he wanted and asked for more!
This confusing and conflicting behavior should stay far away from any attempt to develop a standard linguistic approach to communication which I hope LLMs are aiming to achieve.
If I was chaotic neutral, I'd totally play along with their bluffing and watch them get really confused.
As an Asker, this sounds like an absolute nightmare for me.
(https://www.theatlantic.com/national/2010/05/askers-vs-guess...)
An asker asks for things, absolutely everything, and the giver must choose what they can give.
A guesser must choose what they can ask for, and only ask when they're quite sure it can be given, so the giver has less responsibility for the transfer or service, and most asks can be assumed to be reasonable.
A Persian cannot ask for anything. They must wait for it to be offered, and even then, they must insist that they are quite alright, and that they would rather do without, and only through reciprocal insistence from the giver can they consider whether it would be rude to take them up on the offer.
Presumably, one can judge the giver's underlying intent by the quality of their reciprocal insistence (does it seem like they're just doing the bare minimum of insistence upon their offering, or do they truly wish for me to take them up on it?)
In the Taarof system, an offeree actually has more data, rather than a simpler Asker-scenarion "no", and even more data than the shared values in a Guesser household, this allows for a quick negotiation of values by the immediate and well-practiced cultural norms around the quality of insistence, even for people across different households.
The entire of the Middle East operates on a principle of magnanimous hospitality. The Arabs call this karam, for example, which is considered to even be a religious obligation.
So if you're a stranger passing through a town and chat with some locals, you can expect for someone to invite you for tea and maybe even dinner!
Do you take them up on the offer?
Most people in the West would ask themselves "do I have the time", but a middle easterner would think "do they have the time?" Remember, you as a guest are also magnanimously hospitable--in this case, the least possible burden. Unfortunately, the guest must navigate whether they are being considerate or insulting by refusing hospitality.
Now to address taarof specifically. Persian's have pathologized hosptiality to the point of psychosis. The behavior is often mechanically choreographed (e.g. you should refuse at least twice before accepting a cucumber.) In other cases, it's insane.
Story time:
My mom and aunt had not seen each other for 3 years and met for lunch at a cafe. They went back and forth over who would pay at the register until it erupted into a fight. They sat at separate tables for lunch.
A close family friend--with no provocation from my sister--offered to house her for a weekend she was visiting. My sister accepted. That friend later complained to my mother.
A friend of mine went to a mechanic who offered to fix a small issue for free. My friend knowing better paid him anyway, but the mechanic was still upset since he didn't pay enough!
Edit: Just to address some of the comments. Abroad, the degree of hospitality is warped for foreigners (for what I hope are obvious reasons). Middle easterners in the West are far more inclusive.
If you offer I will assume that you mean it. If you decline my offer I will assume you know best. If you say something I will assume that you mean it.
It was so refreshing to visit New York City. The clerk says “waddya want”, no fake west coast smile, no hollow welcome “I want coffee” Now if someone smiles at me I can assume it’s genuine.
The hard bit of LLMs is making the LLM, not conforming to every set of politeness rules on the planet. An attempt to make a Persian foundation model, created only from Persian-originated technologies, might make that clear.