Related papers: Analyzing Bias in False Refusal Behavior of Large …
Large language models (LLMs) increasingly operate in high-stakes settings including healthcare and medicine, where demographic attributes such as race and ethnicity may be explicitly stated or implicitly inferred from text. However,…
Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…
Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative…
Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using…
Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…
Large Language Models (LLMs) are a transformational technology, fundamentally changing how people obtain information and interact with the world. As people become increasingly reliant on them for an enormous variety of tasks, a body of…
This paper systematically examines nation-level biases exhibited by Large Language Models (LLMs) within the domain of International Relations (IR). Leveraging historical records from the United Nations Security Council (UNSC), we developed…
Large Language Models (LLMs) excel at providing information acquired during pretraining on large-scale corpora and following instructions through user prompts. This study investigates whether the quality of LLM responses varies depending on…
In this study, we explore the use of Large Language Models (LLMs) to counteract hate speech. We conducted the first real-life A/B test assessing the effectiveness of LLM-generated counter-speech. During the experiment, we posted 753…
Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…
While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…
Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to explore more emergent abilities in multimodality. Visual language models (VLMs), such…
Data filtering strategies are a crucial component to develop safe Large Language Models (LLM), since they support the removal of harmful contents from pretraining datasets. There is a lack of research on the actual impact of these…
The rapid integration of Large Language Models (LLMs) into various domains raises concerns about societal inequalities and information bias. This study examines biases in LLMs related to background, gender, and age, with a focus on their…
Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for…
While Large Language Models (LLMs) have become ubiquitous in many fields, understanding and mitigating LLM biases is an ongoing issue. This paper provides a novel method for evaluating the demographic biases of various generative AI models.…
We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…
Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…
In-context learning enables large language models (LLMs) to perform a variety of tasks, including learning to make reward-maximizing choices in simple bandit tasks. Given their potential use as (autonomous) decision-making agents, it is…
Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…