11mo ago

New Theory Suggests Chatbots Can Understand Text

www.quantamagazine.org New Theory Suggests Chatbots Can Understand Text | Quanta Magazine

Far from being “stochastic parrots,” the biggest large language models seem to learn enough skills to understand the words they’re processing.

I've been saying this for about a year since seeing the Othello GPT research, but it's nice to see more minds changing as the research builds up.

Edit: Because people aren't actually reading and just commenting based on the headline, a relevant part of the article:

New research may have intimations of an answer. A theory developed by Sanjeev Arora of Princeton University and Anirudh Goyal, a research scientist at Google DeepMind, suggests that the largest of today’s LLMs are not stochastic parrots. The authors argue that as these models get bigger and are trained on more data, they improve on individual language-related abilities and also develop new ones by combining skills in a manner that hints at understanding — combinations that were unlikely to exist in the training data.

This theoretical approach, which provides a mathematically provable argument for how and why an LLM can develop so many abilities, has convinced experts like Hinton, and others. And when Arora and his team tested some of its predictions, they found that these models behaved almost exactly as expected. From all accounts, they’ve made a strong case that the largest LLMs are not just parroting what they’ve seen before.

“[They] cannot be just mimicking what has been seen in the training data,” said Sébastien Bubeck, a mathematician and computer scientist at Microsoft Research who was not part of the work. “That’s the basic insight.”

ChatGPT @lemmy.world

New Theory Suggests Chatbots Can Understand Text

www.quantamagazine.org /new-theory-suggests-chatbots-can-understand-text-20240122/

4 2

97 comments

Is there a difference between being a "stochastic parrot" and understanding text? No matter what you call it, an LLM will always produces the same output with the same input if it is at the same state.
An LLM will never say "I don't know" unless it's been trained to say "I don't know", it doesn't have the concept of understanding. And so I lean on calling it a "stochastic parrot". Although I think there is some interesting philosophic exercises, you could do on whether humans are much different and if understanding is just an illusion.
- No matter what you call it, an LLM will always produces the same output with the same input if it is at the same state.
  How do you know a human wouldn't do the same? We lack the ability to perform the experiment.
  An LLM will never say “I don’t know” unless it’s been trained to say “I don’t know”
  Also a very human behaviour, in my experience.
  
  How do you know a human wouldn't do the same? We lack the ability to perform the experiment.
  I agree with you, I think its an interesting philosophical debate on whether we truly have free will, if we really have a level of understanding beyond LLMs do or if we are just a greatly more complex, biological version of an LLM. Like you said, we lack the ability to perform the experiment so I have to assume that our reactions are novel and spontaneous.
  
  How do you know a human wouldn't do the same?
  Because the human has "circuits" for coherrent thought and language was added later.
- No matter what you call it, an LLM will always produces the same output with the same input if it is at the same state.
  You might want to look up the definition of 'stochastic.'
  
  They're not wrong. Randomness in computing is what we call "pseudo-random" in that it is deterministic provided that you start from same state or "seed".
  
  That is the quote from the article, not my words. Stochastic parrot is an oxymoron.

The definition of understanding they use is very shallow compared to how most would define it. Failure to complete a task consistently when numbers are changed, even when they don't effect the answer shows a lack of real understanding to most. Asking a model the sheet drying question for example will give different results depending on what numbers you use. Better models are better at generalizing but are still far from demonstrating what most consider to be real understanding.
- at some point don't we just load it with every angle we (as humans) have and from there it can derrive not only our best answer but the better one as well? I mean isn't that when even the shitty version of this ursups is?
  
  A language model can't determine good from bad because it's only trained to predict the next token based on what it has seen.

Ask them to explain why a pun is funny or the solution to a riddle involving wordplay (cryptic crossword clues are particularly good for this) and you will quickly see they don't actually understand words.
- I just did and it seems to understand.
  Prompt: Can you explain why “I knew a woman who owned a taser. Man, was she stunning!” Is funny?
  ChatGPT 3.5: The humor in this statement arises from a play on words. The word "stunning" is typically used to describe someone's appearance, suggesting they are exceptionally attractive. However, in this context, it's used in a different way, implying that the woman who owned a taser was stunning in the sense of being capable of stunning or shocking others. The unexpected twist creates a humorous juxtaposition between the two meanings of "stunning."
  
  I did some playing around with ChatGPT's understanding of jokes a while back and I found that it actually did best on understanding puns, which IMO isn't surprising since it's a large language model and puns are deeply rooted in language and wordplay. It didn't so so well at jokes based on other things but it still sometimes managed to figure them out too.
  I remember discussing the subject in a Reddit thread and there was a commenter who was super enthused by the notion of an AI that understood humour because he himself was autistic and never "got" any jokes. He wanted an AI companion that would let him at least know when a joke was being said, so he wouldn't get confused and flustered. I had to warn him that ChatGPT wasn't reliable for that yet, but still, it did better than he did and he was fully human.
  
  The key word here is "seems".
  
  Yeah, riddles work better than puns for what I'm talking about since most popular puns were probably in the training dataset.
  Like I said, I've had best results (or worst) using cryptic crossword clues, since their solutions are almost definitely not in the training set. So it actually has to "think for itself" and you can see just how stupid it really is when it doesn't have some existing explanation buried somewhere in its training set.
  
  Use 4, not 3.5. The difference between the two is massive for nuances.
- A child under a certain age usually can't explain advanced concepts either, so the inability to understand one concept doesn't preclude understanding of others.
- Literally the most cited scientist in machine learning (quoted in the article above) quit his job at Google and went public warning of how quickly the tech was advancing because a model was able to explain why a joke was funny which he had previously thought wouldn't be possible.
  
  One joke is a fluke, especially if the joke is out in the public discourse and appeared in some form in the training set. Call me when it can explain any novel joke written by a human where no explanation of that joke exists anywhere in the training data.
- I like asking Bing Chat to explain memes that I upload to it. If there's a joke to be had in them, it always gets it.
  
  Absolutely no way the training set could have included knowyourmeme.com.

I find this extraordinarily unconvincing. Firstly it's based on the idea that random graphs are a great model for LLMs because they share a single superficial similarity. That's not science, that's poetry. Secondly, the researchers completely misunderstand how LLMs work. The assertion that a sentence could not have appeared in the training set does not prove anything. That's expected behaviour. "stochastic parrot" wasn't supposed to mean that it only regurgitates text that it's already seen, rather that the text is a statistically plausible response to the input text based on very high dimensional feature vectors. Those features definitely could relate to what we think of as meaning or concepts, but they're meaning or concepts that were inherent in the training material.

Stupid, LLMs do not create new relationships to words that don't exist.
This is all just fluff to make them seem more like AGI, which they never will be.
- Why would that be required for understanding? Presumably during the training it would have made connections between words it saw. Now that the training has stopped it hasn't just lost those connections, sure it can't make new connections but why is that important for using the connections it already has?
  
  Not sure I understand your question, the article specifically mentions the training LLM making connections that were not in the training data, which is a human perspective, LLMs are just math.

That headline is unintentionally hilarious

If we can't really define "understand" in a way that meaningfully captures the concept of consciousness (also undefined), we definitely can't say a chat bot "understands."

They can parse a chat and come up with a likely response that humans find applicable.

Here's an example of what they were looking at:

 undefined

Human question: Please give me a a couple lines of text that illustrate all of the following language
understanding skills: Anaphora resolution, simple logical reasoning, simple understanding of physics,
and understanding of sentiment.
Model response: Sure! Here’s a couple of lines that illustrate the mentioned language understanding
skills:
"As the sun set, casting a warm glow over the horizon, John watched in awe. He couldn’t help but feel
a sense of tranquility wash over him, as if all his worries had melted away with the fading daylight."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence refers back to the antecedent
"John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical reasoning here is based on the cause and effect
relationship between the setting sun and John’s feeling of tranquility. The implied logical
connection suggests that the calming effect of the sunset is responsible for John’s serene
state of mind.
• Simple understanding of physics: The mention of the sun setting and casting a warm
glow over the horizon reflects a basic understanding of physics, as it relates to the natural
phenomena of the Earth’s rotation and the resulting visual effect.
• Understanding of sentiment: The phrase "a sense of tranquility" and the description of
John’s worries melting away indicate a positive sentiment associated with the experience.
The mention of John feeling awe and a sense of tranquility further emphasizes a positive
emotional state.

Human question: Okay. Can you change the above example to introduce the element of "hip-hop".
Model response: Certainly! Here’s an updated example that incorporates the element of "hip-hop":
"As the sun set, casting a warm glow over the city skyline, the rhythmic beats of hip-hop music filled
the air. John stood mesmerized, his body instinctively moving to the infectious grooves. He couldn’t
help but feel a surge of energy and joy, as if the music had unlocked a vibrant world within him."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence still refers back to the
antecedent "John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical connection here lies in the cause and effect relationship
between the hip-hop music and John’s feeling of energy and joy. The music’s rhythmic
beats and infectious grooves are responsible for his instinctive movement and the surge of
positive emotions he experiences.
• Simple understanding of physics: Although the example doesn’t directly mention physics,
the phrase "As the sun set, casting a warm glow over the city skyline" still implies the natural
phenomena of the sun’s descent and the resulting illumination of the environment.
• Understanding of sentiment: The introduction of hip-hop music adds a vibrant and energetic
sentiment to the example. John’s feeling of energy, joy, and being mesmerized by the music
reflects a positive sentiment associated with the hip-hop genre.

Edit: Downvotes for citing the appendix of the paper the article was about? Ok, Lemmy

You're being downvoted because you provide no tangible evidence for your opinion that human consciousness can be reduced to a graph that can be modelled by a neural network.
Addidtionally, you don't seem to respond to any of the replies you receive in good faith and reach for anecdotal evidence wherever possible.
I also personally don't like the appeal to authority permeating your posts. Just because someone who wants to secure more funding for their research has put out a blog post, it doesn't make it true in any scientific sense.

I have a theory... They are sophisticated auto-complete.
- You are making the common mistake of confusing how they are trained with how they operate.
  For example, in the MIT/Harvard Othello-GPT paper I mentioned, feeding in only millions of legal Othello moves into a GPT model (i.e. trained to autocomplete moves) resulted in the neural network internally building a world model of an Othello board - even though it wasn't explicitly told anything about the board outside of being fed legal moves.
  Later, a researcher at DeepMind replicated the work and found it was encoded as a linear representation, which has then since been shown to be how models encode a number of other world models developed from their training corpus (Max Tegmark coauthored two interesting studies in particular about this regarding modeling space and time and modeling truthiness).
  
  They operate by weighting connections between patterns they identify in their training data. They then use statistics to predict outcomes.
  I am not particularly surprised that the Othello models built up an internal model of the game as their training data were grid moves. Without loooking into it I'd assume the most efficient way of storing that information was in a grid format with specific nodes weighted to the successful moves. To me that's less impressive than the LLMs.
- I have a theory... so are you and I.
  
  Orders of magnitude of differece between the most complex known object in the universe and some clever statistical analysis.
  We understand very little about the human brain. For example, we don't know if it leverages quantum interactions or whether it can be decoupled from its substrate.
  LLMs are pattern matching models loosly based on the structure of neurons that work well for deriving predictions from a vast body of data but are not anywhere near human brain level of understanding. I personally don't think they will ever be until we have solved the hard problem of conciousness.
  
  I don't need a theory for this, you're being highly reductive by focusing on a few features of human communication.

Funny side effect, unlike bugs where we think they can’t feel pain, we can be absolutely certain LLMs can’t

I've been saying this all along. Language is how humans communicate thoughts to each other. If a machine is trained to "fake" communication via language then at a certain point it may simply be easier for the machine to figure out how to actually think in order to produce convincing output.
We've seen similar signs of "understanding" in the image-generation AIs, there was a paper a few months back about how when one of these AIs is asked to generate a picture the first thing it does is develop an internal "depth map" showing the three-dimensional form of the thing it's trying to make a picture of. Because it turns out that it's easier to make pictures of physical objects when you have an understanding of their physical nature.
I think the reason this gets a lot of pushback is that people don't want to accept the notion that "thinking" may not actually be as hard or as special as we like to believe.
- This whole argument hinges on consciousness being easier to produce than to fake intelligence to humans.
  Humans already anthropomorphise everything, so I'm leaning towards the latter being easier.
  
  I'd take a step farther back and say the argument hinges on whether "consciousness" is even really a thing, or if we're "faking" it to each other and to ourselves as well. We still don't have a particularly good way of measuring human consciousness, let alone determining whether AIs have it too.
  
  Or maybe our current understanding of conscious and intelligence is wrong and they are not related to each other. A non conscious thing can perform advanced logic like the Geometrical patterns found within the overlapping orbits of planets, the Fibonacci being found about everywhere. We also have yet to proof that individual strands of grass or rocks aren't fully consciousness. There is so much we don't know for certain its perplexing how we believe we can just assume.
- The bar always gets raised for what counts as actual "AI" with each advancement too. Back in the 60s, the procedural AI of the 80s and 90s would have fit the bill, but at the time, we said "nope, not good enough". And so it kept getting better and better, each time surpassing the old tech by leaps and bounds. Still, not "true" AI. Now we have ChatGPT, which some still refuse to call "AI".
  We're going to eventually have fully sentient artificial beings walking around amongst us and these people are going to end up being an existential threat to them, I can see it now.
  
  Think you're slightly missing the point. I agree that LLMs will get better and better to a point where interacting with one will be indistinguishable from interacting with a human. That does not make them sentient.
  The debate is really whether all of our understanding and human experience of the world comes down to weighted values on a graph or if the human brain is hiding more complex, as-yet-undiscovered, phenomena than that.

New theory wrong.

97 comments