Related papers: Status Hierarchies in Language Models
Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these demands conflict reveals a principal hierarchy -- an implicit…
In a refreshing mathematical investigation, Mark (2018) shows that status hierarchy may facilitate the emergence of cooperation in groups. Despite the contribution, the present paper notes that there are limitations in Mark's model that…
Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…
For language-capable interactive robots to be effectively introduced into human society, they must be able to naturally and efficiently communicate about the objects, locations, and people found in human environments. An important aspect of…
As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emotion wheels -- a psychological framework that argues emotions…
Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a…
Humans increasingly delegate decisions to language models, yet whether these systems reproduce or reshape human patterns of discrimination remains unclear. Here we run a large-scale study to analyse whether language models use demographic…
How we should design and interact with social artificial intelligence depends on the socio-relational role the AI is meant to emulate or occupy. In human society, relationships such as teacher-student, parent-child, neighbors, siblings, or…
This study explores the dynamics of trust in artificial intelligence (AI) agents, particularly large language models (LLMs), by introducing the concept of "deferred trust", a cognitive mechanism where distrust in human agents redirects…
AI agents are increasingly deployed and used to make automated decisions that affect our lives on a daily basis. It is imperative to ensure that these systems embed ethical principles and respect human values. We focus on how we can attest…
Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…
Language models often show a preference for using information from specific positions in the input regardless of semantic relevance. While positional bias has been studied in various contexts, from attention sinks to task performance…
As LLMs increasingly act as autonomous agents in interactive and multi-agent settings, understanding their strategic behavior is critical for safety, coordination, and AI-driven social and economic systems. We investigate how payoff…
While stereotypes are well-documented in human social interactions, AI systems are often presumed to be less susceptible to such biases. Previous studies have focused on biases inherited from training data, but whether stereotypes can…
The identity of a speaker influences language comprehension through modulating perception and expectation. This review explores speaker effects and proposes an integrative model of language and speaker processing that integrates distinct…
_Uncertainty expressions_ such as "probably" or "highly unlikely" are pervasive in human language. While prior work has established that there is population-level agreement in terms of how humans quantitatively interpret these expressions,…
Methods and insights from statistical physics are finding an increasing variety of applications where one seeks to understand the emergent properties of a complex interacting system. One such area concerns the dynamics of language at a…
The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…
The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance.…