Related papers: Towards Developmentally Plausible Rewards: Communi…

The ability to pick up on language signals in an ongoing interaction is crucial for future machine learning models to collaborate and interact with humans naturally. In this paper, we present an initial study that evaluates intra-episodic…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of…

Speakers communicate to influence their partner's beliefs and shape their actions. Belief- and action-based objectives have been explored independently in recent computational models, but it has been challenging to explicitly compare or…

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert…

Humans' experience of the world is profoundly multimodal from the beginning, so why do existing state-of-the-art language models only use text as a modality to learn and represent semantic meaning? In this paper we review the literature on…

In this paper, we propose and consider the problem of cooperative language acquisition as a particular form of the ad hoc team play problem. We then present a probabilistic model for inferring a speaker's intentions and a listener's…

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the…

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward functions are specified in a symbolic language captured by…

Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

We propose a large language model based reward decomposition framework for aligning dialogue agents using only a single session-level feedback signal. We leverage the reasoning capabilities of a frozen, pretrained large language model (LLM)…

Language models exhibit complex, diverse behaviors when prompted with free-form text, making it difficult to characterize the space of possible outputs. We study the problem of behavior elicitation, where the goal is to search for prompts…

Despite important progress, conversational systems often generate dialogues that sound unnatural to humans. We conjecture that the reason lies in their different training and testing conditions: agents are trained in a controlled "lab"…

While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of…

In inductive inference, we investigate the learnability of classes of formal languages. We are interested in what classes of languages are learnable in certain learning settings. A class of languages is learnable, if there is a learner that…

This chapter critically examines the potential contributions of modern language models to theoretical linguistics. Despite their focus on engineering goals, these models' ability to acquire sophisticated linguistic knowledge from mere…