Managing AI Risks in an Era of Rapid Progress

In this short consensus paper, we outline risks from upcoming, advanced AI systems. We examine large-scale social harms and malicious uses, as well as an irreversible loss of human control over autonomous AI systems. In light of rapid and continuing AI progress, we propose priorities for AI R&D and governance.

Meta- (out-of-context) learning in neural networks

Brown et al. (2020) famously introduced the phenomenon of in-context learning in large language models (LLMs). We establish the existence of a phenomenon we call meta-out-of-context learning (meta-OCL) via carefully designed synthetic experiments with LLMs. Our results suggest that meta-OCL leads LLMs to more readily "internalize" the semantic content of text that is, or appears to be, broadly useful (such as true statements, or text from authoritative sources) and use it in appropriate circumstances. We further demonstrate meta-OCL in a synthetic computer vision setting, and propose two hypotheses for the emergence of meta-OCL: one relying on the way models store knowledge in their parameters, and another suggesting that the implicit gradient alignment bias of gradient-descent-based optimizers may be responsible. Finally, we reflect on what our results might imply about capabilities of future AI systems, and discuss potential risks. Our code can be found at https://github.com/krasheninnikov/internalization.

Reward Model Ensembles Help Mitigate Overoptimization

Reinforcement learning from human feedback (RLHF) is a standard approach for fine-tuning large language models to follow instructions. As part of this process, learned reward models are used to approximately model human preferences. However, as imperfect representations of the "true" reward, these learned reward models are susceptible to \textit{overoptimization}. Gao et al. (2023) studied this phenomenon in a synthetic human feedback setup with a significantly larger "gold" reward model acting as the true reward (instead of humans) and showed that overoptimization remains a persistent problem regardless of the size of the proxy reward model and training data used. Using a similar setup, we conduct a systematic study to evaluate the efficacy of using ensemble-based conservative optimization objectives, specifically worst-case optimization (WCO) and uncertainty-weighted optimization (UWO), for mitigating reward model overoptimization when using two optimization methods: (a) best-of-n sampling (BoN) (b) proximal policy optimization (PPO). We additionally extend the setup of Gao et al. (2023) to include 25% label noise to better mirror real-world conditions. Both with and without label noise, we find that conservative optimization practically eliminates overoptimization and improves performance by up to 70% for BoN sampling. For PPO, ensemble-based conservative optimization always reduces overoptimization and outperforms single reward model optimization. Moreover, combining it with a small KL penalty successfully prevents overoptimization at no performance cost. Overall, our results demonstrate that ensemble-based conservative optimization can effectively counter overoptimization.

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this popularity, there has been relatively little public work systematizing its flaws. In this paper, we (1) survey open problems and fundamental limitations of RLHF and related methods; (2) overview techniques to understand, improve, and complement RLHF in practice; and (3) propose auditing and disclosure standards to improve societal oversight of RLHF systems. Our work emphasizes the limitations of RLHF and highlights the importance of a multi-faceted approach to the development of safer AI systems.

Thinker: Learning to Plan and Act

We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for hand-crafted planning algorithms by enabling the agent to learn how to plan autonomously and allows for easy interpretation of the agent's plan with visualization. We demonstrate the algorithm's effectiveness through experimental results in the game of Sokoban and the Atari 2600 benchmark, where the Thinker algorithm achieves state-of-the-art performance and competitive results, respectively. Visualizations of agents trained with the Thinker algorithm demonstrate that they have learned to plan effectively with the world model to select better actions. The algorithm's generality opens a new research direction on how a world model can be used in reinforcement learning and how planning can be seamlessly integrated into an agent's decision-making process.

Investigating the Nature of 3D Generalization in Deep Neural Networks

Visual object recognition systems need to generalize from a set of 2D training views to novel views. The question of how the human visual system can generalize to novel views has been studied and modeled in psychology, computer vision, and neuroscience. Modern deep learning architectures for object recognition generalize well to novel views, but the mechanisms are not well understood. In this paper, we characterize the ability of common deep learning architectures to generalize to novel views. We formulate this as a supervised classification task where labels correspond to unique 3D objects and examples correspond to 2D views of the objects at different 3D orientations. We consider three common models of generalization to novel views: (i) full 3D generalization, (ii) pure 2D matching, and (iii) matching based on a linear combination of views. We find that deep models generalize well to novel views, but they do so in a way that differs from all these existing models. Extrapolation to views beyond the range covered by views in the training set is limited, and extrapolation to novel rotation axes is even more limited, implying that the networks do not infer full 3D structure, nor use linear interpolation. Yet, generalization is far superior to pure 2D matching. These findings help with designing datasets with 2D views required to achieve 3D generalization. Code to reproduce our experiments is publicly available: https://github.com/shoaibahmed/investigating_3d_generalization.git

Unifying Grokking and Double Descent

A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokking}, a training dynamic in which a sustained period of near-perfect training performance and near-chance test performance is eventually followed by generalization, as well as the superficially similar \emph{double descent}. These topics have so far been studied in isolation. We hypothesize that grokking and double descent can be understood as instances of the same learning dynamics within a framework of pattern learning speeds. We propose that this framework also applies when varying model capacity instead of optimization steps, and provide the first demonstration of model-wise grokking.

Blockwise Self-Supervised Learning at Scale

Current state-of-the-art deep networks are all powered by backpropagation. In this paper, we explore alternatives to full backpropagation in the form of blockwise learning rules, leveraging the latest developments in self-supervised learning. We show that a blockwise pretraining procedure consisting of training independently the 4 main blocks of layers of a ResNet-50 with Barlow Twins' loss function at each block performs almost as well as end-to-end backpropagation on ImageNet: a linear probe trained on top of our blockwise pretrained model obtains a top-1 classification accuracy of 70.48%, only 1.1% below the accuracy of an end-to-end pretrained network (71.57% accuracy). We perform extensive experiments to understand the impact of different components within our method and explore a variety of adaptations of self-supervised learning to the blockwise paradigm, building an exhaustive understanding of the critical avenues for scaling local learning rules to large networks, with implications ranging from hardware design to neuroscience.

On The Fragility of Learned Reward Functions

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on the performance of policies trained alongside the reward function. This practice, however, may fail to detect learned rewards that are not capable of training new policies from scratch and thus do not capture the intended behavior. Our work focuses on demonstrating and studying the causes of these relearning failures in the domain of preference-based reward learning. We demonstrate with experiments in tabular and continuous control environments that the severity of relearning failures can be sensitive to changes in reward model design and the trajectory dataset composition. Based on our findings, we emphasize the need for more retraining-based evaluations in the literature.