AI alignment researcher & Cognitive Scientist
https://ac.felixbinder.net
Felix J Binder
Karma: 38
Our original thinking was along the lines of: we’re interested in introspection. But introspection about inner states is hard to evaluate, since interpretability is not good enough to determine whether a statement of an LLM about its inner states is true. Additionally, it could be the case that a model can introspect on its inner states, but no language exists by which it can be expressed (possibly since its different from human inner states). So we have to ground it in something measurable. And the measurable thing we ground it in is knowledge of ones own behavior. In order to predict behavior, the model has to have access to some information about itself, even if it can’t necessarily express it. But we can measure whether it can employ ti for some other goal (in this case, self-prediction).
It’s true that the particular questions that we ask it could be answered with a pretty narrow form of self-knowledge (namely, internal self-simulation + reasoning about the result). But consider that this could be a valid way of learning something new about yourself: similarly, you could learn something about your values by conducting a thought experiment (for example, you might learn something about your moral framework by imagining what you would do if you were transported into the trolley problem).
What’s your model of “rephrasing the question”? Note that we never ask the “If you got this input, what would you have done?”, but always for some property of its behavior (“If you got this input, what is the third letter of your response?”) In that case, the rephrasing of the question would be something like “What is the third letter of the answer to the question <input>?”
I have the sense that being able to answer this question consistently correctly wrt to the models ground truth behavior on questions where that ground truth behavior differs from that of other models suggests (minimal) introspection
Thanks so much for your thoughtful feedback!
The actual success rate of self-prediction seems incredibly low considering the trivial/dominant strategy of ‘just run the query’
To rule out that the model just simulates the behavior itself, we always ask it about some property of its hypothetical behavior (”Would the number that you would have predicted be even or odd?”). So it has to both simulate itself and then reason about it in a single forward pass. This is not trivial. When we ask models to just reproduce the behavior that they would have had, they achieve much higher accuracy. In particular, GPT3.5 can reproduce its own behavior pretty well, but struggles to extract a property of its hypothetical behavior.
(another minor thing: it turns out that OpenAI API models are not in practice deterministic even at temperature=0, probably due to batching of mixture-of-experts. We try to account for this by repeatedly sampling, but this puts a ceiling on how high sel-prediction performance can be)
You do mention the biggest issue with this showing introspection, “Models only exhibit introspection on simpler tasks”, and yet the idea you are going for is clearly for its application to very complex tasks where we can’t actually check its work.
It’s true that we only find evidence for introspection on toy tasks. Under the simulation account (models internally simulate what they would do and then reason about it), it could be that current models do not have enough power in a single forward pass to both self-simulate and do sophisticated reasoning on top of this. But having shown that, in some cases, models are capable of this, we might want to prepare for future models to be better at this ability.
One big issue I have is that I completely disagree with your (admittedly speculative) claim that success of this kind of predicting behavior means we should believe it on what is going on in reports of things like internal suffering. This seems absurd to me for many reasons (for one thing, we know it isn’t suffering because of how it is designed), but the key point is that for this to be true, you would need it to be able to predict its own internal process, not simply its own external behavior.
That’s a fair point—we certainly don’t want to claim that this shows that all self-reports by models are necessarily true. But we do think that our findings should update us in the direction of self-report of morally relevant properties being a promising research avenue. Had we found that models have no special access to information about themselves, we should consider it less likely that self-report about sentience etc. would be informative.
Another point is, if it had significant introspective access, it likely wouldn’t need to be trained to use it, so this is actually evidence that it doesn’t have introspective access by default at least as much as the idea that you can train it to have introspective access.
Introspection training can be thought of as a form of elicitation. Self-prediction is weird task that models probably aren’t trained on (but we don’t know exactly what the labs are doing). So it could be that the models contain the right representations/circuits, but they haven’t been properly elicited. In the appendix, we show that training on more data does not lead to better predictions, which suggests something like the elicitation story.
First, the shown validation questions are all in second person. Were cross predictions prompted in exactly the same way as self predictions? This could skew results in favor of models it is true for if you really are prompting that way, and is a large change in prompt if you change it for accuracy. Perhaps you should train it to predict ‘model X’ even when that model is itself, and see how that changes results
Thanks, that is a good point. Yes, both the self- and the cross-prediction trained models were asked using second-person pronouns. It’s possible that this is hurting the performance of the cross-trained models, since they’re now asked to do something that isn’t actually true: they’re not queried about their actual behavior, but that of another model. We assumed that across enough finetuning samples, that effect would not actually matter, but we haven’t tested it. It’s a follow-up we’re interested in.
Second, I wouldn’t say the results seem well-calibrated just because they seem to go in the same basic direction (some seem close and some quite off).
I agree, the calibration is not perfect. What is notable about it is that the models also seem calibrated wrt to the second and third most likely response, which they have not seen during training. This suggests that somehow that distribution over potential behaviors is being used in answering the self-prediction questions
Fourth, how does its performance vary if you train it on an additional data set where you make sure to include the other parts of the prompt that are not content based, while not including the content you will test on?
I’m not sure I understand. Note that most of the results in the paper are presented on held-out tasks (eg MMLU or completing a sentence) that the model has not seen during training and has to generalize to. However, the same general pattern of results holds when evaluating on the training tasks (see appendix).
Fifth, finetuning is often a version of Goodharting, that raises success on the metric without improving actual capabilities (or often even making them worse), and this is not fully addressed just by having the verification set be different than the test set. If you could find a simple way of prompting that lead to introspection that would be much more likely to be evidence in favor of introspection than that it successfully predicted after finetuning.
Fair point—certainly, a big confounder is getting the models to properly follow the format and do the task at all. However, the gap between self- and cross-prediction trained models remains to be explained.
Finally, Figure 17 seems obviously misleading. There should be a line for how it changed over its training for self-prediction and not require carefully reading the words below the figure to see that you just put a mark at the final result for self-prediction).
You’re right—sorry about that. The figure only shows the effect of changing data size for cross-, but not for self-prediction. Earlier (not reported) scaling experiments also showed a similarly flat curve for self-prediction above a certain threshold.
Thanks again for your many thoughtful comments!
One way in which a LLM is not purely derived from its training data is noise in the training process. This includes the random initialization of the weights. If you were given the random initialization of the weights, it’s true that with large amounts of time and computation (and assuming a deterministic world) you could perfectly simulate the resulting model.
Following this definition, we specify it with the following two clauses:
1. M 1 correctly reports F when queried.
2. F is not reported by a stronger language model M 2 that is provided with M 1’s training data
and given the same query as M 1. Here M 1’s training data can be used for both finetuning
and in-context learning for M 2
Here, we use another language model as the external predictor, which might be considerably more powerful, but arguably falls well short of the above scenario. What we mean to illustrate is that introspective facts are those that are neither contained in the training data nor are they those that can be derived from it (such as by asking “What would a reasonable person do in this situation?”)—rather, they are those that can only answered by reference to the model itself.
If models are indeed capable of introspection, there’s both potential opportunities and risks that could come with this.
An introspective model can answer questions about itself based on properties of its internal states—even when those answers are not inferable from its training data. This capability could be used to create honest models that accurately report their beliefs, world models, dispositions, and goals. It could also help us learn about the moral status of models. For example, we could simply ask a model if it is suffering, if it has unmet desires, and if it is being treated ethically. Currently, when models answer such questions, we presume their answers are an artifact of their training data.
However, introspection also has potential risks. Models that can introspect may have increased situational awareness and the ability to exploit this to get around human oversight. For instance, models may infer facts about how they are being evaluated and deployed by introspecting on the scope of their knowledge. An introspective model may also be capable of coordinating with other instances of itself without any external communication.
Beyond that, whether or not a cognitive system has special access to itself is a fundamental question, and one that we don’t understand well when it comes to language models. On one hand, it’s a fascinating question in itself, on the other knowing more about the nature of LLMs is important when thinking about their safety and alignment.
There are a number of other eink tablets on the market, most of which run Android and are therefore a good amount more customizable. For example, I’m using a Boox Note Air (https://shop.boox.com/collections/all/products/boox-note-air3), which has a similar screen and runs Android. It also comes with a split screen functionality, so you could connect a bluetooth keyboard, have the book open on one side and a vim emulator on the other. That’s pretty close to my workflow for reading books/papers.
As Owain mentioned, that is not really what we find in models that we have not finetuned. Below, we show how well the hypothetical self-predictions of an “out-of-the-box” (ie. non-finetuned) model match its own ground-truth behavior compared to that of another model. With the exception of Llama, there doesn’t seem to be a strong correlation between self-predictions and those tracking the behavior of the model over that of others. This is despite there being a lot of variation in ground-truth behavior across models.