Garbage in, gold out?
Don't classify, hallucinate
81–90 of 118 posts
Re: Don't classify, hallucinate
#82TIL LLMs follow Cunningham's Law, or they claim to be.
Re: Don't classify, hallucinate
#83Jeopardy clustering
Pretty cool technique honestly. You could do it the other way as well right?
If you had a list of categories you have the model to generate a sample query and then do embedding on that?
Re: Don't classify, hallucinate
#84Earlier quoted context omitted.
> On two occasions I have been asked, – "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?" ... I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question. He clearly didn't know enough about vector embeddings.
Unironically, LLM is absolutely amazing at giving you the right answers when you put in wrong input, compared to every other algorithm ever invented.
That’s one of the properties that distinguishes intelligence from traditional deterministic algorithms.
Re: Don't classify, hallucinate
#85I can’t believe programming is now at the stage where advice like "first have the computer give you totally wrong answers, then just find a function that maps the wrong answers to the correct ones!" is a thing.
The terminology is misleading you.
“Hallucinate” is misleading here. In the given example, a classification is being done very successfully - it’s just that it requires an extra step to map it to an arbitrary predefined list of classifications.
If you can articulate why you think this isn’t a good approach, I’d be interested to hear it.
Re: Don't classify, hallucinate
#86Earlier quoted context omitted.
Unironically, LLM is absolutely amazing at giving you the right answers when you put in wrong input, compared to every other algorithm ever invented.
That’s one of the properties that distinguishes intelligence from traditional deterministic algorithms.
I feel like I'm fighting a losing battle but I don't see why so many people consider LLMs innately non-deterministic, an LLM running on a CPU with greedy decoding would be 100% deterministic and still have the intelligence we associate with LLMs
Re: Don't classify, hallucinate
#87Earlier quoted context omitted.
> On two occasions I have been asked, – "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?" ... I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question. He clearly didn't know enough about vector embeddings.
Unironically, LLM is absolutely amazing at giving you the right answers when you put in wrong input, compared to every other algorithm ever invented.
I was hoping a lossy semantic reasoning machine would put to bed words such as "right" and "wrong" outside of formal logic, but apparently this fight has just begun
Re: Don't classify, hallucinate
#88Earlier quoted context omitted.
That’s one of the properties that distinguishes intelligence from traditional deterministic algorithms.
I feel like I'm fighting a losing battle but I don't see why so many people consider LLMs innately non-deterministic, an LLM running on a CPU with greedy decoding would be 100% deterministic and still have the intelligence we associate with LLMs
Valid point, it’s why I included the word “traditional”, to try to qualify that.
What I meant is something more like explicitly programmed vs. learned. Intelligence can result from learned behavior, but not from explicit programming of rules by humans.
An aspect of this is that “learning” is unpredictable - we can’t predict in advance exactly how the resulting model will behave, except broadly. It seems non-deterministic if only by virtue of its complexity, which is beyond anything we’re able to predictively model.
Re: Don't classify, hallucinate
#89A common case I have is when you don't have classifications to begin with. For example, you need to find what users complain about most. I take embeddings of all records, then cluster the embeddings into semantic groups, then ask an LLM to take a random sample from each clustered group and create a classification for that group. This method is sensitive to the thresholds (what is the maximum distance between embeddin…
The idea of distance thresholding models that are trained to satisfy an ordering constraint is a bit strange. The reason it's hard is that there isn't a threshold!
You can slice and dice it a ton of different ways, but the significance of groups is incidental.
It's a good starting point, but having done this a few times for a few companies it always seems like it needs substantial human review.
Re: Don't classify, hallucinate
#90I would try using structured outputs recursively.
```
Request 1: "brown coffee table: " + {Root Schema} => "Furniture"
Request 2: "brown coffee table: Furniture / " + {Furniture Schema} => "Living Room Furniture"
Request 3: "brown coffee table: Furniture / Living Room Furniture / " + {Living Room Furniture Schema} => "Coffee Tables"
```
Many more round trips, but classifying products is not a latency sensitive task.