相关论文: Do they mean 'us'? Interpreting Referring Expressi…

Current studies of bias in NLP rely mainly on identifying (unwanted or negative) bias towards a specific demographic group. While this has led to progress recognizing and mitigating negative bias, and having a clear notion of the targeted…

Studies of human psychology have demonstrated that people are more motivated to extend empathy to in-group members than out-group members (Cikara et al., 2011). In this study, we investigate how this aspect of intergroup relations in humans…

Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity assignments lead LLMs…

This study investigates ``us versus them'' bias, as described by Social Identity Theory, in large language models (LLMs) under both default and persona-conditioned settings across multiple architectures (GPT-4.1, DeepSeek-3.1, Gemma-2.0,…

Large language models (LLMs) are supposed to acquire unconscious human knowledge and feelings, such as social common sense and biases, by training models from large amounts of text. However, it is not clear how much the sentiments of…

Drawing on constructs from psychology, prior work has identified a distinction between explicit and implicit bias in large language models (LLMs). While many LLMs undergo post-training alignment and safety procedures to avoid expressions of…

Ingroup favoritism, the tendency to favor ingroup over outgroup, is often explained as a product of intergroup conflict, or correlations between group tags and behavior. Such accounts assume that group membership is meaningful, whereas…

Generative Large Language Models (LLMs) infer user's demographic information from subtle cues in the conversation -- a phenomenon called implicit personalization. Prior work has shown that such inferences can lead to lower quality responses…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Multi-party linguistic entrainment refers to the phenomenon that speakers tend to speak more similarly during conversation. We first developed new measures of multi-party entrainment on features describing linguistic style, and then…

While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this…

Intergroup contact has long been considered as an effective strategy to reduce prejudice between groups. However, recent studies suggest that exposure to opposing groups in online platforms can exacerbate polarization. To further understand…

The rapid deployment of artificial intelligence (AI) models demands a thorough investigation of biases and risks inherent in these models to understand their impact on individuals and society. This study extends the focus of bias evaluation…

When a student fails an exam, do we tend to blame their effort or the test's difficulty? Attribution, defined as how reasons are assigned to event outcomes, shapes perceptions, reinforces stereotypes, and influences decisions. Attribution…

Large language models (LLMs) are becoming pervasive in everyday life, yet their propensity to reproduce biases inherited from training data remains a pressing concern. Prior investigations into bias in LLMs have focused on the association…

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…

Language is a popular resource to mine speakers' attitude bias, supposing that speakers' statements represent their bias on concepts. However, psychology studies show that people's explicit bias in statements can be different from their…

Recent researches indicate that Pre-trained Large Language Models (LLMs) possess cognitive constructs similar to those observed in humans, prompting researchers to investigate the cognitive aspects of LLMs. This paper focuses on explicit…

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…