Linux

48376 readers

1322 users here now

From Wikipedia, the free encyclopedia

Linux is a family of open source Unix-like operating systems based on the Linux kernel, an operating system kernel first released on September 17, 1991 by Linus Torvalds. Linux is typically packaged in a Linux distribution (or distro for short).

Distributions include the Linux kernel and supporting system software and libraries, many of which are provided by the GNU Project. Many Linux distributions use the word "Linux" in their name, but the Free Software Foundation uses the name GNU/Linux to emphasize the importance of GNU software, causing some controversy.

Rules

Posts must be relevant to operating systems running the Linux kernel. GNU/Linux or otherwise.
No misinformation
No NSFW content
No hate speech, bigotry, etc

Related Communities

Community icon by Alpár-Etele Méder, licensed under CC BY 3.0

founded 5 years ago

MODERATORS

AgreeableLandscape@lemmy.ml

nooter692@lemmy.ml

MarcellusDrum@lemmy.ml

cypherpunks@lemmy.ml

cyclohexane@lemmy.ml

d3Xt3r@lemmy.nz

299

Microsoft says a Copilot key is coming to keyboards on Windows PCs starting this month (www.cnbc.com)

submitted 10 months ago by mr_MADAFAKA@lemmy.ml to c/linux@lemmy.ml

215 comments fedilink hide all child comments

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

[–] kogasa@programming.dev 7 points 10 months ago (1 children)

Semantic embeddings are a thing. LLMs "work with tokens" but they associate them with semantic models internally. You can externalize it via semantic embeddings so that the same semantic models can be shared between LLMs.

[–] lvxferre@lemmy.ml 4 points 10 months ago* (last edited 10 months ago)

The source that I've linked mentions semantic embedding; so does further literature on the internet. However, the operations are still being performed with the vectors resulting from the tokens themselves, with said embedding playing a secondary role.

This is evident for example through excerpts like

The token embeddings map a token ID to a fixed-size vector with some semantic meaning of the tokens. These brings some interesting properties: similar tokens will have a similar embedding (in other words, calculating the cosine similarity between two embeddings will give us a good idea of how similar the tokens are).

Emphasis mine. A similar conclusion (that the LLM is still handling the tokens, not their meaning) can be reached by analysing the hallucinations that your typical LLM bot outputs, and asking why that hallu is there.

What I'm proposing is deeper than that. It's to use the input tokens (i.e. morphemes) only to retrieve the sememes (units of meaning; further info here) that they're conveying, then discard the tokens themselves, and perform the operations solely on the sememes. Then for the output you translate the sememes obtained by the transformer into morphemes=tokens again.

I believe that this would have two big benefits:

The amount of data necessary to "train" the LLM will decrease. Perhaps by orders of magnitude.
A major type of hallucination will go away: self-contradiction (for example: states that A exists, then that A doesn't exist).

And it might be an additional layer, but the whole approach is considerably simpler than what's being done currently - pretending that the tokens themselves have some intrinsic value, then playing whack-a-mole with situations where the token and the contextually assigned value (by the human using the LLM) differ.

[This could even go deeper, handling a pragmatic layer beyond the tokens/morphemes and the units of meaning/sememes. It would be closer to what @njordomir@lemmy.world understood from my other comment, as it would then deal with the intent of the utterance.]