[dvt]

An alarming number of people don't understand that LLMs work via purely stochastic processes, so I'm happy to see in-depth pieces like this. I'm looking for a job and maybe this is why it's so hard to get a callback these days: resumes are just dumped in some LLM black hole and no one really knows how it works. The author says:

> temperature 0.1 — low, supposedly nudging the model toward deterministic outputs

This is not correct (and is briefly touched on later in the piece when he sets temperature to 0), temperature is not some kind of "deterministic" switch, but rather it affects the sampling distribution (which becomes more "spiky"—but is still very much a distribution).

[miki123211]

In theory, temperature 0 does make the LLM deterministic.

Well, in theory theory, temperature 0 doesn't really exist. Mathematically, as lim temperature->0, the distribution gets spikier and spikier, the most likely sample goes to almost-but-not-quite infinity and the rest go to almost-but-not-quite 0. In practice, temperature=0 is literally a separate branch of an if statement that just picks the most common sample (using the actual formula that works for non-zero values would cause a zero division).

However, due to things such as batching and even different kinds of floating point imprecisions for different algorithm implementations, the probability distribution itself often differs run-by-run, so what you sample from it also differs.

[sigmoid10]

>in theory theory, temperature 0 doesn't really exist.

It does exist very much, even if you go to pure math. Look at the softmax function and take the limit as T->0. It becomes a dirac-delta function. I.e. in a discrete setting (like for LLMs with a finite set of output tokens), probability P becomes one for argmax and 0 for everything else. Only in coding practice it is easer to implement T=0 as a simple if check that directly chooses argmax instead of calculating the limit of some function that includes 1/T quotients. But setting T to zero is in both, theory and practice, turning the usual probability function into greedy sampling.

[aesthesia]

A distribution with all probability mass on one outcome is deterministic, so in principle, setting temperature to 0 _should_ result in deterministic outputs. There are a few reasons it might not, but I don't think any of these apply when running a local model like the author did.

[317070]

> so in principle, setting temperature to 0 _should_ result in deterministic outputs

It is a common misconception, but it is not true even in principle. If I have 2 or more logits which are equal to the maximum of my logits, I will sample uniformly random from them with any temperature, even zero. Sampling from softmax([1, 0, 1]) is still stochastic at temperature 0, because the limit is to sample uniformly from the first or the last element.

Anyway: "GPUs don't do deterministic matrix multiplications" is the biggest source of randomness in LLMs. GPUs put the associativity of the sums in matrix multiplications in arbitrary order, and this has a huge impact on the logits coming out of the neural network.

[EvgeniyZh]

You don't have to sample uniformly. You could take the lowest index of all maxima. But yeah, the main source of randomness is non-deterministic matmul, and temperature does nothing with it

[easygenes]

There are. If the kernels are nondeterministic (e.g. timing issues) there are minor changes between runs, on a single system, even with eager decode enabled (typically what temperature=0 achieves).

[croes]

So you would get always the same result, but it could be the wrong one

[valzam]

I mean the easiest explanation would be that the model harness doesn't always take the most likely token but does top-k sampling or similar. temperatur just means that probabilities get more and more equalized, boosting the chance that an unlikely token gets picked. but even with temp 0 you could have 0.8 T1, 0.19 T2, ... and sometimes sample T2

[aesthesia]

No, this can't happen at temperature 0. The formula defining temperature-adjusted softmax isn't strictly defined at 0, but taking the limit (in the case where all logits are distinct) results in probability 1 being placed on the largest logit. Samplers will typically special case temperature 0 and pick the most likely token at each step.

[dvt]

This is a very authoritative answer that should be more nuanced and caveated as implementation-dependent. In some cases, repetition penalties take precedence over sampling; top_k and top_p can also be handled before or after the temperature step. In other cases, `0` is turned into like 1e-10 or some super tiny float value (which can drift if you do any arithmetic with it). Routing, quantization, etc. can also have an effect on sampling. And yes, in some cases, setting temperature to 0 can mean "pure greedy decoding" which makes the decoder about as deterministic as it can get.

[IshKebab]

Setting the temperature to 0 should give deterministic results but that's not any better - it's just hiding the huge variance by only taking one sample.

[bluechair]

Willing to be corrected but I believe this type of automated resume filtering is illegal. Not saying it never happens but my understanding is it is not typical.

[thayne]

I would expect that to depend on jurisdiction.

I don't know for sure, but I would be surprised if it was illegal in my particular US state. You might be able to argue the AI has inherent biases that introduce illegal discrimination in the hiring process, but my understanding is winning I case like that would be very difficult, especially since most employers are very cagey about their hiring process and why they mades a decision.

[small_scombrus]

They don't need to actually filter/blackhole to have have the same virtual effect.

Show someone a list of resumes with an "applicant score*" and they'll naturally ignore the ones with a low ranking

*scores are generated with AI, mistakes may be made, use only as a guide and verify results

[ivan_gammel]

In situations when you get hundreds of applications for one open position (real market now), whatever reduces your pool to the size a human can handle, works. You can preserve some diversity metrics in the process. This particular filtering is rather primitive, but LLM as a first filter can definitely do the job. You may burn less tokens than the hourly rate of your HR and it will be fairer than just dumping 50% of unread CVs in trash.

[369548684892826]

Great until someone realises you’ve filtered out minority groups from the application process (most developers are men so maybe the LLM decided they’re the best fit, but you’ll never know exactly why it screwed your over) and you suddenly have an expensive lawsuit

[elric]

Under GDPR, you have the right to request manual processing whenever personal data is processed automatically to make a decision about you that has "significant impact". Not being hired seems like it would qualify.

[dgellow]

Illegal where?

[spwa4]

> An alarming number of people don't understand that LLMs work via purely stochastic processes ...

I've been studying AI for 20 years. What really needs to be added to this statement is:

"An alarming number of people don't understand that LLMs work via purely stochastic processes - and so does human thinking. People do NOT arrive at the same conclusion if merely the weather's different. Worse: with human thinking not only do most people not think this is real, a subset of people will actively fight the idea. Of course, depending on the weather"

[miki123211]

What's even worse, different humans have different weights.

If you train two different LLMs and replace what data they "see" in batch n, that doesn't affect the data they see in batch n+1, or any further batches. In LLMs, you can introduce "noise" into the training process, but that noise doesn't really compound.

Humans learn from experience, not from data, and their experiences at age n shape what experiences they seek (and hence train on) at age n+1. A small amount of "noise" injected into their "training", let's say hearing a group of friends discuss a movie while their identical tween goes to the bathroom, can compound into them watching that movie, which can compound into them forming an identity around that genre, and so on, until they're two completely different people, trained on completely different "data mixtures".

[smusamashah]

We expect computers to be consistent on the other hand. A calculator will always give you the same answer unless some chip gets struck by a particle. LLMs are on computers and should be fairly consistent too.

[mnky9800n]

Test retest reliability is a thing in psychometrics.

[make3]

A more spikey distribution exactly makes the distribution closer to deterministic. That's not the point though. Even in greedy (deterministic) decoding, it is still a black box though that reacts in ways ways that are unpredictable to the inputs. Switching one word around might lead to different scores for example.