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

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

arxiv.org

Post reply on HN
Print view View original

11–20 of 54 posts

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#11

Post by WithinReason »

zmgsabst wrote: post #6

“A is B” doesn’t generally entail “B is A”. “A square is a rectangle” does not entail “a rectangle is a square”. Similarly, “Socrates is alive” doesn’t entail “alive is Socrates”. Notably, they mention when context is included, LLM performance rises — ie, exactly when we include extra information that allows it to recognize what kind of information is being conveyed. But the LLM is correct not to generalize that patt…

That completely misses the point. The point is that "Valentina Tereshkova was the first woman to travel to space" does imply "The first woman to travel to space was Valentina Tereshkova", which LLMs fail to recognise.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#12

Post by altmanaltman »

beardyw wrote: post #8
gipp wrote: post #5

As I and several other people pointed out last time this was posted, "A is B," in natural language, does not imply "B is A." "Is" can denote any of many different shades of relationship weaker than logical identity.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

Why would it have several answer when you are asking for a singular child?

Isn't the right way to phrase that question be "Who are Mary Lee Pfeiffer's children?" to get multiple answers?

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#13

Post by trumpdong »

ralferoo wrote: post #9

Not only is the inverse not generally true (as others have pointed out), their examples requires several mental leaps. "Who is Tom Cruise's mother? [A: Mary Lee Pfeiffer]" and the reverse "Who is Mary Lee Pfeiffer's son?" The word "mother" has no relationship to "son" in terms of the model, and so while the model might be able to infer a proximity relationship between "Tom Cruise" and "Mary Lee Pfeiffer" just because…

Pretraining could be reasonably expected to make it learn that mother/father and son/daughter are inverse relationships and Tom is usually a male name.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#14

Post by whilenot-dev »

beardyw wrote: post #8
gipp wrote: post #5

As I and several other people pointed out last time this was posted, "A is B," in natural language, does not imply "B is A." "Is" can denote any of many different shades of relationship weaker than logical identity.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

It could have several correct answers, yes, where one should be logically deducible.

"Mary Lee Pfeiffer (A) is Tom Cruise's (B's) mother" and "Tom Cruise (B) is Mary Lee Pfeiffer's (A's) son" are two statements of the same relation.

EDIT: I mean if you'd go so far, even Tom Cruise could have multiple mothers, but that doesn't make "Mary Lee Pfeiffer is Tom Cruise's mother" a wrong statement, just because "one of ... mothers" is missing.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#15

Post by IshKebab »

WithinReason wrote: post #11
zmgsabst wrote: post #6

“A is B” doesn’t generally entail “B is A”. “A square is a rectangle” does not entail “a rectangle is a square”. Similarly, “Socrates is alive” doesn’t entail “alive is Socrates”. Notably, they mention when context is included, LLM performance rises — ie, exactly when we include extra information that allows it to recognize what kind of information is being conveyed. But the LLM is correct not to generalize that patt…

That completely misses the point. The point is that "Valentina Tereshkova was the first woman to travel to space" does imply "The first woman to travel to space was Valentina Tereshkova", which LLMs fail to recognise.

Right, but that could be because the fact that that implication exists is not actually as trivial as they are implying.

Does "Flargbler was blorglargh" imply "blorglargh was Flargbler"? Maybe. You need more context to know.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#16

Post by beardyw »

altmanaltman wrote: post #12
beardyw wrote: post #8

Earlier quoted context omitted.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

Why would it have several answer when you are asking for a singular child? Isn't the right way to phrase that question be "Who are Mary Lee Pfeiffer's children?" to get multiple answers?

A single person would satisfy my question but it needn't be Tom Cruise.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#17

Post by niam »

altmanaltman wrote: post #12
beardyw wrote: post #8

Earlier quoted context omitted.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

Why would it have several answer when you are asking for a singular child? Isn't the right way to phrase that question be "Who are Mary Lee Pfeiffer's children?" to get multiple answers?

Your question arguably doesn't have multiple answers. There's one answer: the set of children (discounting different orders of the set).

The question "Who is her child" has multiple answers because it asks you to deliver a single answer.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#18

Post by latexr »

beardyw wrote: post #8
gipp wrote: post #5

As I and several other people pointed out last time this was posted, "A is B," in natural language, does not imply "B is A." "Is" can denote any of many different shades of relationship weaker than logical identity.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

> "Who is Mary Lee Pfeiffer's child?" would have several.

Might have several. It only has one answer if there is only one child, which appears to be the case here. They are measuring against what they told the model, not necessarily facts mapping to the real world.

In this case, the correct would always include “Tom Cruise” even if it needed a clarifying “there might be others I have no knowledge of”.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#19

Post by sigmoid10 »

beardyw wrote: post #8
gipp wrote: post #5

As I and several other people pointed out last time this was posted, "A is B," in natural language, does not imply "B is A." "Is" can denote any of many different shades of relationship weaker than logical identity.

Yes, "Who is Mary Lee Pfeiffer's son?" happens to have just one answer, whereas "Who is Mary Lee Pfeiffer's child?" would have several.

I wouldn't resort to language examples, as the other comments show how this gets imprecise and lost in semantic details quickly. Instead think of a basic logic example: Consider an OR gate with inputs A and B and output X. If B=1 that means X=1. But if X=1 you can't infer that B=1, because there is an alternative (i.e. A=1,B=0). So from B=1→X=1, the inverse simply does not follow. This extends to all statements where a relation is not symmetric. Of course you can also go beyond and find cases where the relationship is not transitive or not even reflexive. There's a whole branch of language based IQ test puzzles (e.g. "all X are Y, some Y are Z" kind of stuff) that exploit this rabbit hole. Any LLM that does good on these will not jump to conclusions about reverse equalities quickly.

Re: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" (2023)

#20

Post by Dylan16807 »

gipp wrote: post #5

As I and several other people pointed out last time this was posted, "A is B," in natural language, does not imply "B is A." "Is" can denote any of many different shades of relationship weaker than logical identity.

That's a fine reaction to the title alone but a very bad reaction to the abstract, where the failure they're criticizing is real and not a childish misunderstanding of the word "is".

Is the abstract misleading and the full paper is stupider than the upfront examples? If not this criticism seems like a total waste of time.

Post reply on HN