Cognitive bias in high-stakes decision-making with llms
Large language models (LLMs) offer significant potential as tools to support an expanding
range of decision-making tasks. However, given their training on human (created) data …
range of decision-making tasks. However, given their training on human (created) data …
Cognitive bias in decision-making with LLMs
Large language models (LLMs) offer significant potential as tools to support an expanding
range of decision-making tasks. Given their training on human (created) data, LLMs have …
range of decision-making tasks. Given their training on human (created) data, LLMs have …
Metrics for What, Metrics for Whom: Assessing Actionability of Bias Evaluation Metrics in NLP
This paper introduces the concept of actionability in the context of bias measures in natural
language processing (NLP). We define actionability as the degree to which a measure's …
language processing (NLP). We define actionability as the degree to which a measure's …
The devil is in the neurons: Interpreting and mitigating social biases in language models
Pre-trained Language models (PLMs) have been acknowledged to contain harmful
information, such as social biases, which may cause negative social impacts or even bring …
information, such as social biases, which may cause negative social impacts or even bring …
A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
Y Xu, L Hu, J Zhao, Z Qiu, Y Ye, H Gu - arXiv preprint arXiv:2404.00929, 2024 - arxiv.org
Based on the foundation of Large Language Models (LLMs), Multilingual Large Language
Models (MLLMs) have been developed to address the challenges of multilingual natural …
Models (MLLMs) have been developed to address the challenges of multilingual natural …
Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and
there is well-documented evidence of demographic bias in these systems. In languages …
there is well-documented evidence of demographic bias in these systems. In languages …
Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models
Attributing answers to source documents is an approach used to enhance the verifiability of
a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on …
a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on …
BiasWipe: Mitigating Unintended Bias in Text Classifiers through Model Interpretability
Toxic content detection plays a vital role in addressing the misuse of social media platforms
to harm people or groups due to their race, gender or ethnicity. However, due to the nature …
to harm people or groups due to their race, gender or ethnicity. However, due to the nature …
Mitigating social bias in sentiment classification via ethnicity-aware algorithmic design
Sentiment analysis tools are frequently employed to analyze large amounts of natural
language data gathered from social networks and generate valuable insights on public …
language data gathered from social networks and generate valuable insights on public …
MAFIA: Multi-Adapter Fused Inclusive LanguAge Models
Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent
studies have identified various biases that such models exhibit and have proposed methods …
studies have identified various biases that such models exhibit and have proposed methods …