相关论文: Gender Differences in Motivated Reasoning

Large Language Models have achieved remarkable performance on reasoning tasks, motivating research into how this ability evolves during training. Prior work has primarily analyzed this evolution via explicit generation outcomes, treating…

Like many scientific disciplines, neuroscience has increasingly attempted to confront pervasive gender imbalances within the field. While much of the conversation has centered around publishing and conference participation, recent research…

Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy…

The existence of gender differences in the structure and composition of social networks is a well established finding in the social and behavioral sciences, but researchers continue to debate whether structural, dispositional, or life…

In this study, headcounts of all personnel in Nobel Prize-winning labs were collected and sorted by gender. These results are used to determine gender representation of graduate students in elite institutions on the pipeline towards higher…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which…

For the first time, we report gender bias in people's choice and use of password managers, through a semi-structured interview ($n=18$) and a questionnaire-based survey ($n=200$, conducted `in the wild'). Not only do women and men prefer…

Pre-trained language models trained on large-scale data have learned serious levels of social biases. Consequently, various methods have been proposed to debias pre-trained models. Debiasing methods need to mitigate only discriminatory bias…

When faced with a polar question, speakers often provide overinformative answers going beyond a simple "yes" or "no". But what principles guide the selection of additional information? In this paper, we provide experimental evidence from…

Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in…

Beliefs shape how people reason, communicate, and behave. Rather than existing in isolation, they exhibit a rich correlational structure--some connected through logical dependencies, others through indirect associations or social processes.…

When humans judge the affective content of texts, they also implicitly assess the correctness of such judgment, that is, their confidence. We hypothesize that people's (in)confidence that they performed well in an annotation task leads to…

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting…

Qualitative and quantitative approaches to reasoning about uncertainty can lead to different logical systems for formalizing such reasoning, even when the language for expressing uncertainty is the same. In the case of reasoning about…

Artificial intelligence (AI) is becoming increasingly complex, making it difficult for users to understand how the AI has derived its prediction. Using explainable AI (XAI)-methods, researchers aim to explain AI decisions to users. So far,…

AI and ML models have already found many applications in critical domains, such as healthcare and criminal justice. However, fully automating such high-stakes applications can raise ethical or fairness concerns. Instead, in such cases,…

In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can…

We study how motivated reasoning affects the provision of climate policy in an electoral competition framework. Voters experience anticipatory disutility when future outcomes appear grim and may therefore distort beliefs in response to…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…