[HN Gopher] AbsenceBench: Language models can't tell what's missing
___________________________________________________________________
AbsenceBench: Language models can't tell what's missing
Author : JnBrymn
Score : 27 points
Date : 2025-06-20 22:26 UTC (33 minutes ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| AlienRobot wrote:
| Unrelated to the paper, which is about asking LLM's to figure out
| which parts of a document were removed, but my assumption has
| been that to an LLM there is nothing "missing" in the sense that
| any input leads to valid computation and output.
|
| For example, I asked ChatGPT to explain something I typed
| randomly
|
| >It looks like you've entered "dosfi8q3anfdfiqr", which appears
| to be a random string or perhaps a typo--it's not a recognized
| acronym, code, or term in any common context I'm aware of. Could
| you share a bit more about where you found this?
|
| Although the answer is correct, my point is that anything you
| give to the LLM is going to be put under some bucket. The LLM
| can't say "I don't know what that is." Instead it says "that is a
| random string." As far as the LLM is concerned, it knows every
| possible input and concept that anyone could ever type into it,
| it's just that its "understanding" of what that means (after the
| tokens have gone through the neural network) doesn't necessarily
| match what any human being thinks it means.
| cs702 wrote:
| Interesting. Even the most recent models perform relatively
| poorly when asked to identify which information in a context has
| been removed, given access to both the original and edited
| contexts.
|
| The authors posit that poor performance is due to the fact that
| the attention mechanism of Transformers cannot attend to the
| removed tokens, because there are no keys for them!
|
| Thank you for sharing on HN.
___________________________________________________________________
(page generated 2025-06-20 23:00 UTC)