I don’t know if this is true. But I haven’t seen an LLM spit out 50 token sequences of training data. By definition (an LLM as a “compressor”) this shouldn’t happen.
Which sets of data that you get is fairly random, and it is likely mixing different sets as well to some degree.
Oddly, other online LLMs do not seem to be as easy to fool.
- They don’t do compression by “definition”. They are designed to predict, prediction is key to information theory, so they just have similar qualities.
- Everyone wants their model to learn, not copy data, but overfitting happens sometimes and overfitting can look the same as copying.
Is there really any difference?
A little like random number generation vs data corruption…
Output may look the same, but one is done on purpose and one means your system is going to crap.
A couple problems with this.
1) That's not the definition of an LLM, it's just a useful way to think about it.
2) That is exactly what I'd expect a compressor to do. That's the exact job of lossless compression.
Of course the metaphor is lossy compression, not lossless. But it's not that surprising if lossy compression reproduces some piece of what it compressed. A jpeg doesn't get every pixel or every local group of pixels wrong.
It depends on how lossy the compression is?
sorry what? TFA does not mention RAG at all. are you reading your own biases into this or did i miss something