11 accepted papers
While reinforcement learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO). Existing approaches address ROO by adding KL regularization, requiring computationally expensive hyperparameter tuning. Additionally, KL regularization…
Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning. Whilst much work has been done to formulate useful auxiliary objectives, their construction is still an art which proceeds b…
The spontaneous exchange of turns is a central aspect of human communication. Although turn-taking conventions come to us naturally, artificial dialogue agents struggle to coordinate, and must rely on hard-coded rules to engage in interactive conversations with human interlocutors. In this paper, we…
Despite evidence from cognitive sciences that larger groups of speakers tend to develop more structured languages in human communication, scaling up to populations has failed to yield significant benefits in emergent multi-agent communication. In this paper we advocate for an alternate population-le…
As machine learning models are deployed ever more broadly, it becomes increasingly important that they are not only able to perform well on their training distribution, but also yield accurate predictions when confronted with distribution shift. The Distributionally Robust Optimization (DRO) framewo…
Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous work has shown that agents trained to play this game with reinforcement learning…
In most settings of practical concern, machine learning practitioners know in advance what end-task they wish to boost with auxiliary tasks. However, widely used methods for leveraging auxiliary data like pre-training and its continued-pretraining variant are end-task agnostic: they rarely, if ever,…
A central goal of machine learning is to learn robust representations that capture the fundamental relationship between inputs and output labels. However, minimizing training errors over finite or biased datasets results in models latching on to spurious correlations between the training input/outpu…
Distributionally robust optimization (DRO) provides a framework for training machine learning models that are able to perform well on a collection of related data distributions (the "uncertainty set"). This is done by solving a min-max game: the model is trained to minimize its maximum expected loss…
To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model could potentially be trained better with a scorer that “adapts…
Multi-headed attention is a driving force behind recent state-of-the-art NLP models. By applying multiple attention mechanisms in parallel, it can express sophisticated functions beyond the simple weighted average. However we observe that, in practice, a large proportion of attention heads can be re…