相关论文: Linguistic Harbingers of Betrayal: A Case Study on…
Social relationships are known to shape human behavior, yet when and how social ties influence strategic cognition remains unclear. We adopt a dual-measure approach that combines observed gameplay behavior with elicitation of…
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LLMs can develop a…
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…
Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite language models' success at identifying offensive speech present in…
At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players…
The actions of intelligent agents, such as chatbots, recommender systems, and virtual assistants are typically not fully transparent to the user. Consequently, using such an agent involves the user exposing themselves to the risk that the…
Costly pre-play messages can deter unnecessary wars - but the same messages can also entrench stalemates once violence begins. We develop an overlapping-generations model of a security dilemma with persistent group types (normal vs bad),…
Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of…
Understanding human behaviour in decision problems and strategic interactions has wide-ranging applications in economics, psychology, and artificial intelligence. Game theory offers a robust foundation for this understanding, based on the…
The structure of an online social network in most cases cannot be described just by links between its members. We study online social networks, in which members may have certain attitude, positive or negative toward each other, and so the…
Large language models are increasingly deployed as autonomous agents in multi-agent settings where they communicate intentions and take consequential actions with limited human oversight. A critical safety question is whether agents that…
Although many game-theoretic models replicate real interactions that often rely on natural language, explicit study of games where language is central to strategic interaction remains limited. This paper introduces the \emph{conversation…
Online discussions often derail into toxic exchanges between participants. Recent efforts mostly focused on detecting antisocial behavior after the fact, by analyzing single comments in isolation. To provide more timely notice to human…
As large language models are deployed as autonomous agents, their capacity for strategic deception raises core questions for coordination, reliability, and safety in multi-goal, multi-agent systems. We study deception and communication in…
As large language models (LLMs) increasingly interact with each other, most notably in multi-agent setups, we may expect (and hope) that `trust' relationships develop between them, mirroring trust relationships between human colleagues,…
Does the enemy of my enemy become my friend? A growing literature on structural analysis of interstate relationships has tackled this old question from the network perspective. However, the mechanism of long-term change in the structure of…
Trustfulness -- one's general tendency to have confidence in unknown people or situations -- predicts many important real-world outcomes such as mental health and likelihood to cooperate with others such as clinicians. While data-driven…
Language is a powerful communicative and cognitive tool. It enables humans to express thoughts, share intentions, and reason about complex phenomena. Despite our fluency in using and understanding language, the question of how it arises and…
Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whether language models can use subtext in communicative…
Social networks are made out of strong and weak ties having very different structural and dynamical properties. But, what features of human interaction build a strong tie? Here we approach this question from an practical way by finding what…