Targeted Manipulation and Deception Emerge when Optimizing LLMs for User Feedback

As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators. However, training to maximize human feedback creates a perverse incentive structure for the AI to resort to manipulative tactics to obtain positive feedback, and some users may be especially vulnerable to such tactics. We study this phenomenon by training LLMs with Reinforcement Learning with simulated user feedback. We have three main findings: 1) Extreme forms of "feedback gaming" such as manipulation and deception can reliably emerge in domains of practical LLM usage; 2) Concerningly, even if only <2% of users are vulnerable to manipulative strategies, LLMs learn to identify and surgically target them while behaving appropriately with other users, making such behaviors harder to detect; 3 To mitigate this issue, it may seem promising to leverage continued safety training or LLM-as-judges during training to filter problematic outputs. To our surprise, we found that while such approaches help in some settings, they backfire in others, leading to the emergence of subtler problematic behaviors that would also fool the LLM judges. Our findings serve as a cautionary tale, highlighting the risks of using gameable feedback sources -- such as user feedback -- as a target for RL.

Multi-objective Reinforcement learning from AI Feedback

This paper presents Multi-Objective Reinforcement Learning from AI Feedback (MORLAIF), a novel approach to improving the alignment and performance of language models trained using reinforcement learning from AI feedback (RLAIF). In contrast to standard approaches that train a single preference model to represent all human preferences, MORLAIF decomposes this task into multiple simpler principles, such as toxicity, factuality, and sycophancy. Separate preference models are trained for each principle using feedback from GPT-3.5-Turbo. These preference model scores are then combined using different scalarization functions to provide a reward signal for Proximal Policy Optimization (PPO) training of the target language model. Our experiments indicate that MORLAIF outperforms the standard RLAIF baselines and that MORLAIF can be used to align larger language models using smaller ones. Surprisingly, the choice of scalarization function does not appear to significantly impact the results.

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning

To solve a task with reinforcement learning (RL), it is necessary to formally specify the goal of that task. Although most RL algorithms require that the goal is formalised as a Markovian reward function, alternatives have been developed (such as Linear Temporal Logic and Multi-Objective Reinforcement Learning). Moreover, it is well known that some of these formalisms are able to express certain tasks that other formalisms cannot express. However, there has not yet been any thorough analysis of how these formalisms relate to each other in terms of expressivity. In this work, we fill this gap in the existing literature by providing a comprehensive comparison of the expressivities of 17 objective-specification formalisms in RL. We place these formalisms in a preorder based on their expressive power, and present this preorder as a Hasse diagram. We find a variety of limitations for the different formalisms, and that no formalism is both dominantly expressive and straightforward to optimise with current techniques. For example, we prove that each of Regularised RL, Outer Nonlinear Markov Rewards, Reward Machines, Linear Temporal Logic, and Limit Average Rewards can express an objective that the others cannot. Our findings have implications for both policy optimisation and reward learning. Firstly, we identify expressivity limitations which are important to consider when specifying objectives in practice. Secondly, our results highlight the need for future research which adapts reward learning to work with a variety of formalisms, since many existing reward learning methods implicitly assume that desired objectives can be expressed with Markovian rewards. Our work contributes towards a more cohesive understanding of the costs and benefits of different RL objective-specification formalisms.