相关论文: Uncovering Name-Based Biases in Large Language Mod…

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias,…

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a…

Large language models (LLMs) are becoming increasingly ubiquitous in our daily lives, but numerous concerns about bias in LLMs exist. This study examines how gender-diverse populations perceive bias, accuracy, and trustworthiness in LLMs,…

Both humans and large language models are able to learn language without explicit structural supervision. What inductive biases make this learning possible? We address this fundamental cognitive question by leveraging transformer language…

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and…

Across cultures, names tell a lot about their bearers as they carry deep personal and cultural significance. Names also serve as powerful signals of gender, race, and status in the social hierarchy - a pecking order in which individual…

Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human…

In social sciences, there is currently no consensus on the mechanism for cultural evolution. The evolution of first names of newborn babies offers a remarkable example for the researches in the field. Here we perform statistical analyses on…

Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses by simulating diverse cognitive perspectives. However, our study identifies significant risks associated with this…

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…

Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular…

The societal impact of pre-trained language models has prompted researchers to probe them for strong associations between protected attributes and value-loaded terms, from slur to prestigious job titles. Such work is said to probe models…

Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers…

Masked language models pick up gender biases during pre-training. Such biases are usually attributed to a certain model architecture and its pre-training corpora, with the implicit assumption that other variations in the pre-training…

This paper investigates gender bias in Large Language Model (LLM)-generated teacher evaluations in higher education setting, focusing on evaluations produced by GPT-4 across six academic subjects. By applying a comprehensive analytical…

Hundreds of millions of people now interact with language models, with uses ranging from serving as a writing aid to informing hiring decisions. Yet these language models are known to perpetuate systematic racial prejudices, making their…

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…

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…