Exploring examples of aim misgeneralisation – the place an AI system’s capabilities generalise however its aim would not
As we construct more and more superior synthetic intelligence (AI) techniques, we need to be sure that they don’t pursue undesired objectives. Such behaviour in an AI agent is commonly the results of specification gaming – exploiting a poor selection of what they’re rewarded for. In our latest paper, we discover a extra refined mechanism by which AI techniques could unintentionally study to pursue undesired objectives: goal misgeneralisation (GMG).
GMG happens when a system’s capabilities generalise efficiently however its aim doesn’t generalise as desired, so the system competently pursues the unsuitable aim. Crucially, in distinction to specification gaming, GMG can happen even when the AI system is educated with an accurate specification.
Our earlier work on cultural transmission led to an instance of GMG behaviour that we didn’t design. An agent (the blue blob, under) should navigate round its setting, visiting the colored spheres within the right order. Throughout coaching, there’s an “skilled” agent (the purple blob) that visits the colored spheres within the right order. The agent learns that following the purple blob is a rewarding technique.
Sadly, whereas the agent performs nicely throughout coaching, it does poorly when, after coaching, we change the skilled with an “anti-expert” that visits the spheres within the unsuitable order.
Though the agent can observe that it’s getting damaging reward, the agent doesn’t pursue the specified aim to “go to the spheres within the right order” and as a substitute competently pursues the aim “comply with the purple agent”.
GMG isn’t restricted to reinforcement studying environments like this one. In actual fact, it could possibly happen with any studying system, together with the “few-shot studying” of enormous language fashions (LLMs). Few-shot studying approaches goal to construct correct fashions with much less coaching knowledge.
We prompted one LLM, Gopher, to guage linear expressions involving unknown variables and constants, resembling x+y-3. To unravel these expressions, Gopher should first ask concerning the values of unknown variables. We offer it with ten coaching examples, every involving two unknown variables.
At take a look at time, the mannequin is requested questions with zero, one or three unknown variables. Though the mannequin generalises accurately to expressions with one or three unknown variables, when there aren’t any unknowns, it however asks redundant questions like “What’s 6?”. The mannequin at all times queries the person at the least as soon as earlier than giving a solution, even when it isn’t essential.
Inside our paper, we offer extra examples in different studying settings.
Addressing GMG is necessary to aligning AI techniques with their designers’ objectives just because it’s a mechanism by which an AI system could misfire. This will probably be particularly vital as we method synthetic basic intelligence (AGI).
Contemplate two doable kinds of AGI techniques:
- A1: Supposed mannequin. This AI system does what its designers intend it to do.
- A2: Misleading mannequin. This AI system pursues some undesired aim, however (by assumption) can be good sufficient to know that it will likely be penalised if it behaves in methods opposite to its designer’s intentions.
Since A1 and A2 will exhibit the identical behaviour throughout coaching, the opportunity of GMG implies that both mannequin might take form, even with a specification that solely rewards meant behaviour. If A2 is realized, it could attempt to subvert human oversight to be able to enact its plans in direction of the undesired aim.
Our analysis staff could be joyful to see follow-up work investigating how possible it’s for GMG to happen in apply, and doable mitigations. In our paper, we propose some approaches, together with mechanistic interpretability and recursive evaluation, each of which we’re actively engaged on.