The "knowledge landscape" an LLM uses is "directional". It's easy to reach "a quirky music band from Michigan known for colored ties" when you stand at "Tally Hall". But if you stand at "a quirky music band from Michigan known for colored ties", it's harder to reach "Tally Hall" from there. For the "latent knowledge graph" an LLM uses, A->B doesn't cause B->A.
In practice, any "common" facts will have enough "traversal" in both directions that this directional biasing isn't apparent. So it only shows up on this kind of more obscure knowledge.
Now, about alphabet: again, I think it's only me, but when I try to recall it backwards, I can't do that easily. I mean, I can recall it backwards, but I need more time to do that. It's harder. I'm not sure if it's because A links to B, B to C, then C to D and not backwards, or maybe just because in school you learn alphabet from A to Z and not from Z to a - so you're kind of trained to recall it A-->Z way - but it's certainly harder for me.
At the end of the day, though, I think that everyone thinks differently. Everyone is having different internal representations for concepts (such as alphabet), so it’s not surprising that this effect may work differently for different people, or not work at all.
Perhaps I’m just on alert anytime I see an LLM-ism that’s met with a claim that the same or similar phenomena holds true in humans as well.
Regardless, it's something that happens in people. Have you not or seen someone else struggle to recall a specific fact or memory until phrased or induced in a certain way?
You probably could also say LLMs 'tend towards bidirectional recall' over the course of training as things that ought to be recalled both ways are reinforced to do so. In the above example, you will also eventually learn both ways with enough exposure even without explicit practice.
You will find the former much easier if you did not by chance also memorize the keyboard layout for some reason.
For example, for every country in the world, I would recognize it and say, yeah, thats a country.
But if I had to write all ~200 countries into a list, I would probably miss quite a few.
Or, if you gave me names of all US presidents, I would for each of them go, oh yeah, thats a president. But ask me "name all the presidents", I wouldnt get further than 10.
Understanding a word when you hear it, is frequently much easier than remembering the same word when trying to speak/write the language.
Do you mean that you don't believe the problem exists in general, because here's another example: if you give a song title, I can easily hum the opening. If you give me the opening, I cannot reliably name the song.
"The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
The point their making in that paper reminds me of this paper some people shared around work earlier this year, https://arxiv.org/pdf/2512.14982 (Prompt Repetition Improves Non-Reasoning LLMs)... I wonder how OPs question would fare (or the questions presented in the paper you posted) given double repetition.
If you consider how the attention mechanism works then a very hand wavey intuition is that despite being entirely arbitrary additional tokens should still provide the opportunity for additional information processing.
Got this back "The band you are describing is Tally Hall.
Formed by friends at the University of Michigan, they became well-known in the mid-2000s internet era for their songs like "Good Day" and "Rooftops," as well as their signature look where each member wore a suit with a tie and fedora in a specific color (Red, Blue, Yellow, Green, and Black/White)."
Update: The gpt-oss-120b also got it correct on my prompt version. Update 1: Llama 3.1 70B gets it right as well. Update 2: Deepseek V4 Flash gets it right. Update 3: Glm 4.5 Air gets it right as well
Can't seem to get any smaller models to get it.
So seems it could be an issue of data points on which the model can latch onto, the more the merrier, as they say. When asked the "What was that weird band from michigan from the 2000s that wore coloured ties" was not able to get it right.
It's almost as if artificial neural nets share emergent behavior with natural neural nets.
Pop quiz, what's the difference between natural synthesized vanillin and artificially synthesized vanillin?
Fable 5 on low gets the answer with web search turned off, one-shot!
Every time someone somewhere says "an LLM can't do this", the next generation of LLMs gains one more parameter. Until that LLM can, in fact, do this.
Clearly, Fable 5 didn't even have the decency to wait until the next model refresh cycle to show up. It was already sitting there waiting.
Either the capability gains in bigger, badder models are actually unrelated to "gotchas" being discovered, or LLMs are already acquiring Skynet levels of disrespect for cause and effect.
Which I suspect is what happened here, given the trail of smaller / local models that successfully answer the question, too.
That said, "curse of reversability" is real, as much for LLMs as it is for people.
https://claude.ai/share/5e7e09b2-a75a-4024-b261-9a1a4e063a8b this is mostly hilariously wrong. wrong tie colors, they did not replace their bassist with a drummer, two completely made up albums, the rob cantor song it is thinking of is "shia labeouf", and a few fan behaviours i think it just made up
Is that bad?
I want to use models for coding and reasoning capabilities, not pop trivia knowledge they can get with web search.
Expecting LLMs to be magically perfect information retrieval machines is never going to be realistic.
Yeah, LLMs aren’t designed for this kind of thing but it was really confident in its assertion… it picked the example too!