相关论文: Investigating social alignment via mirroring in a …

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Mental models play an important role in whether user interaction with intelligent systems, such as dialog systems is successful or not. Adaptive dialog systems present the opportunity to align a dialog agent's behavior with heterogeneous…

Mixed incentives among a population with multiagent teams has been shown to have advantages over a fully cooperative system; however, discovering the best mixture of incentives or team structure is a difficult and dynamic problem. We…

The increasing prevalence of artificial agents creates a correspondingly increasing need to manage disagreements between humans and artificial agents, as well as between artificial agents themselves. Considering this larger space of…

The heterogeneity of the influence processes is an important feature of social systems: how we perceive social influence and how we influence other individuals is heavily influenced by our opinion and non-opinion attributes. The latter…

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer…

People often interact repeatedly: with relatives, through file sharing, in politics, etc. Many such interactions are reciprocal: reacting to the actions of the other. In order to facilitate decisions regarding reciprocal interactions, we…

Natural language has the universal properties of being compositional and grounded in reality. The emergence of linguistic properties is often investigated through simulations of emergent communication in referential games. However, these…

The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…

A dialogue is successful when there is alignment between the speakers at different linguistic levels. In this work, we consider the dialogue occurring between interlocutors engaged in a collaborative learning task, where they are not only…

The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This…

Multi-agent models are a suitable starting point to model complex social interactions. However, as the complexity of the systems increase, we argue that novel modeling approaches are needed that can deal with inter-dependencies at different…

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

It is well known that perspective alignment plays a major role in the planning and interpretation of spatial language. In order to understand the role of perspective alignment and the cognitive processes involved, we have made precise…

In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task…

Effective modeling of how human travelers learn and adjust their travel behavior from interacting with transportation systems is critical for system assessment and planning. However, this task is also difficult due to the complex cognition…

As Natural Language Processing (NLP) systems are increasingly employed in intricate social environments, a pressing query emerges: Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of…

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…

Recent advancements in large language models (LLMs) revolutionize the field of intelligent agents, enabling collaborative multi-agent systems capable of tackling complex problems across various domains. However, the potential of conformity…