Technology

70942 readers

3430 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago

MODERATORS

L3s@lemmy.world

enu@lemmy.world

technopagan@lemmy.world

L4s@lemmy.world

L3s@hackingne.ws

L4s@hackingne.ws

261

I'm looking for an article showing that LLMs don't know how they work internally (feddit.it)

submitted 6 days ago* (last edited 6 days ago) by lgsp@feddit.it to c/technology@lemmy.world

72 comments fedilink hide all child comments

I found the aeticle in a post on the fediverse, and I can't find it anymore.

The reaserchers asked a simple mathematical question to an LLM ( like 7+4) and then could see how internally it worked by finding similar paths, but nothing like performing mathematical reasoning, even if the final answer was correct.

Then they asked the LLM to explain how it found the result, what was it's internal reasoning. The answer was detailed step by step mathematical logic, like a human explaining how to perform an addition.

This showed 2 things:

LLM don't "know" how they work
the second answer was a rephrasing of original text used for training that explain how math works, so LLM just used that as an explanation

I think it was a very interesting an meaningful analysis

Can anyone help me find this?

EDIT: thanks to @theunknownmuncher @lemmy.world https://www.anthropic.com/research/tracing-thoughts-language-model its this one

EDIT2: I'm aware LLM dont "know" anything and don't reason, and it's exactly why I wanted to find the article. Some more details here: https://feddit.it/post/18191686/13815095

you are viewing a single comment's thread
view the rest of the comments

[–] theunknownmuncher@lemmy.world 5 points 5 days ago (1 children)

You're confusing the confirmation that the LLM cannot explain it's under-the-hood reasoning as text output, with a confirmation of not being able to reason at all. Anthropic is not claiming that it cannot reason. They actually find that it performs complex logic and behavior like planning ahead.

[–] adespoton@lemmy.ca 1 points 5 days ago (1 children)

No, they really don’t. It’s a large language model. Input cues instruct it as to which weighted path through the matrix to take. Those paths are complex enough that the human mind can’t hold all the branches and weights at the same time. But there’s no planning going on; the model can’t backtrack a few steps, consider different outcomes and run a meta analysis. Other reasoning models can do that, but not language models; language models are complex predictive translators.

[–] theunknownmuncher@lemmy.world 8 points 5 days ago (1 children)

To write the second line, the model had to satisfy two constraints at the same time: the need to rhyme (with "grab it"), and the need to make sense (why did he grab the carrot?). Our guess was that Claude was writing word-by-word without much forethought until the end of the line, where it would make sure to pick a word that rhymes. We therefore expected to see a circuit with parallel paths, one for ensuring the final word made sense, and one for ensuring it rhymes.

Instead, we found that Claude plans ahead. Before starting the second line, it began "thinking" of potential on-topic words that would rhyme with "grab it". Then, with these plans in mind, it writes a line to end with the planned word.

🙃 actually read the research?

[–] glizzyguzzler@lemmy.blahaj.zone 1 points 2 days ago

No, they’re right. The “research” is biased by the company that sells the product and wants to hype it. Many layers don’t make think or reason, but they’re glad to put them in quotes that they hope peeps will forget were there.