相关论文: Simulating Identity, Propagating Bias: Abstraction…

The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…

Traditional sociological research often relies on human participation, which, though effective, is expensive, challenging to scale, and with ethical concerns. Recent advancements in large language models (LLMs) highlight their potential to…

Large Language Models (LLMs) are increasingly used in everyday life and research. One of the most common use cases is conversational interactions, enabled by the language generation capabilities of LLMs. Just as between two humans, a…

Research on Large Language Models (LLMs) has often neglected subtle biases that, although less apparent, can significantly influence the models' outputs toward particular social narratives. This study addresses two such biases within LLMs:…

Recent research has explored LLMs as scalable tools for relevance labeling, but studies indicate they are susceptible to priming effects, where prior relevance judgments influence later ones. Although psychological theories link personality…

Endowing dialogue agents with persona information has proven to significantly improve the consistency and diversity of their generations. While much focus has been placed on aligning dialogues with provided personas, the adaptation to the…

In recent years, Large Language Models have attracted growing interest for their significant potential, though concerns have rapidly emerged regarding unsafe behaviors stemming from inherent stereotypes and biases. Most research on…

Stereotypes in large language models (LLMs) can perpetuate harmful societal biases. Despite the widespread use of models, little is known about where these biases reside in the neural network. This study investigates the internal mechanisms…

Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant features, from…

Effective personalized feedback is critical to students' literacy development. Though LLM-powered tools now promise to automate such feedback at scale, LLMs are not language-neutral: they privilege standard academic English and reproduce…

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

As modern Large Language Models (LLMs) shatter many state-of-the-art benchmarks in a variety of domains, this paper investigates their behavior in the domains of ethics and fairness, focusing on protected group bias. We conduct a two-part…

Surveys are widely used in social sciences to understand human behavior, but their implementation often involves iterative adjustments that demand significant effort and resources. To this end, researchers have increasingly turned to large…

Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs'…

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

Large Language Models (LLMs) have demonstrated human-like capabilities in language comprehension and generation, becoming active participants in social and cognitive domains. This study investigates whether LLMs exhibit personality-like…

Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness critical. A significant and underexplored risk is intentional deception, where an LLM deliberately fabricates…

Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it is a literary device. It is also a…

In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this…

This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's…