Abstract AI safety researchers often rely on LLM “judges” to qualitatively evaluate the output of separate LLMs. We try this for our own interpretability research, but find that our LLM judges are often deeply biased. For example, we use Llama2 to judge whether movie reviews are more “(A) positive” or...
Tl;dr: An optimal CIRL agent is corrigible under a certain problem formulation and given certain assumptions. By examining three key assumptions—that the game is played only once, that the human is rational, and that human feedback is free—we demonstrate how minor changes can lead to incorrigible CIRL agents. This suggests...
OpenAI did this too, with GPT-4 pre-release. It was a small program, though — I think just 5-10 researchers.
This is so interesting. I had no idea that this was a thing! I would have assumed that test-writers wrote all of the answers out, then used a (pseudo-)randomizer to order them. But if that really is a pattern in multiple choice tests, it makes absolute sense that Llama would pick up on it.
I suspect that if you ask the model to reconsider its answer, it would double down even on the incorrect (B-biased) responses. LLMs really like being self-consistent. We haven’t run this experiment, but if you do, let us know the result!
If I understand correctly, your proposed fix is something like supervised finetuning on adversarial examples that trigger the B-bias. We can access the output logits directly (replacing step 1) and the ground-truth answer is provided in the dataset (removing the need for step 2), so this seems relatively doable.
The main challenges that I see are 1) the computational cost of doing additional optimization (we had to do best-of-N optimization rather than updating the entire model to make our experiments manageable) and 2) it requires finetuning access (which often isn’t available for the latest models). But these challenges aren’t insurmountable, so I wonder why I haven’t seen finetuned “judges” more often.
AI safety researchers often rely on LLM “judges” to qualitatively evaluate the output of separate LLMs. We try this for our own interpretability research, but find that our LLM judges are often deeply biased. For example, we use Llama2 to judge whether movie reviews are more “(A) positive” or “(B) negative”, and find that it almost always answers “(B)”, even when we switch the labels or order of these alternatives. This bias is particularly surprising for two reasons: first, because we expect a fairly capable model like Llama2 to perform well at a simple sentiment classification task like this, and second, because this specific “(B)”-bias doesn’t map on to a human bias... (read 1796 more words →)
I’d be interested to see this as well!
Thank you for such a detailed and thorough answer! This resolves a lot of my confusion.
Based on conversations around closing the wework Lightcone office, I had assumed that you didn't want to continue hosting office space, and so hadn't considered that counterfactual cost. But the Inn expenses you mention seem more reasonable if the alternative is continuing to rent wework space.
The FTX context also makes a lot of sense. I was confused how the purchase fit into your current strategy and funding situation, but I understand that both of those were quite different a year or two ago. Given how much things have changed, do you have conditions under which you would decide to sell the space and focus on other projects? Or are you planning to hold onto it no matter what, and decide how best to use it to support your current strategy as that develops?
These all sound like major benefits to owning the venue yourself!
To be clear, I don't doubt at all that using the Inn for events is much better than non-purpose-built space. However, the Inn also has costs that renting existing spaces wouldn't: I assume that purchasing and renovating it costs more than renting hotel spaces as-needed for events (though please correct me if I'm wrong!), and my impression is that it's taken the Lightcone team a lot of time and effort over the past year+ to purchase and renovate, which naturally has opportunity costs.
I'm asking because my uninformed guess is that those financial and time costs outweigh the (very real) benefits of hosting... (read more)
Will much of that $3-6M go into renovating and managing the Rose Garden Inn, or to cover work that could have been covered by existing funding if the Inn wasn't purchased?
If so, I'm curious to hear more about the strategy behind buying and renovating the space, since it seems like a substantial capital investment, and a divergence from LightCone Infrastructure's previous work and areas of expertise. I'm aware that several (primarily social?) events were held there over the past year, and I see from an earlier comment that you're planning to host SERI MATS scholars, and to continue providing space for events and retreats.
it seems valuable to have a central and optimized... (read more)
I agree that human model misspecification is a severe problem, for CIRL as well as for other reward modeling approaches. There are a couple of different ways to approach this. One is to do cognitive science research to build increasingly accurate human models, or to try to just learn them. The other is to build reward modeling systems that are robust to human model misspecification, possibly by maintaining uncertainty over possible human models, or doing something other than Bayesianism that doesn't rely on a likelihood model. I’m more sympathetic to the latter approach, mostly because reducing human model misspecification to zero seems categorically impossible (unless we can fully simulate human minds, which... (read more)
Tl;dr: An optimal CIRL agent is corrigible under a certain problem formulation and given certain assumptions. By examining three key assumptions—that the game is played only once, that the human is rational, and that human feedback is free—we demonstrate how minor changes can lead to incorrigible CIRL agents. This suggests that corrigibility is highly sensitive to the underlying assumptions, and we should be wary of assuming that formal corrigibility results will transfer to real-world systems. However, our results do gesture at a class of near-corrigible behavior that may be protective against the most catastrophic outcomes. It may make more sense to consider corrigibility as a continuum rather than a binary. We call for... (read 3415 more words →)
Thanks for the clarification! From OpenAI's announcement, it looks like this ranking only occurs during the finetuning portion of training (Step 2). But the user doesn't have the opportunity to provide this feedback after deployment. So are you suggesting that ChatGPT gets aligned to the values of the human contractor(s) that provide data during finetuning, and then carries these values forward when interacting with users? I'm asking because one of the key benefits of CIRL games (also called "assistance games") is that they allow the AI to continuously update towards the user's values, without freezing for deployment, and I don't fully understand the connection here.
It was a secretive program — it wasn’t advertised anywhere, and we had to sign an NDA about its existence (which we have since been released from). I got the impression that this was because OpenAI really wanted to keep the existence of GPT4 under wraps. Anyway, that means I don’t have any proof beyond my word.