Related papers: Bi-directional Bias Attribution: Debiasing Large L…
Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases. These biases often manifest as unintended associations between neutral concepts and sensitive human…
There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…
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 to correct these biases. However, most of the works address a…
Model attribution for LLM-generated disinformation poses a significant challenge in understanding its origins and mitigating its spread. This task is especially challenging because modern large language models (LLMs) produce disinformation…
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS). These models, trained on massive…
Citation practices are crucial in shaping the structure of scientific knowledge, yet they are often influenced by contemporary norms and biases. The emergence of Large Language Models (LLMs) introduces a new dynamic to these practices.…
Recent advances in large language models (LLMs) have enabled automatic generation of chain-of-thought (CoT) reasoning, leading to strong performance on tasks such as math and code. However, when reasoning steps reflect social stereotypes…
The use of language models (LMs) has increased considerably in recent years, and the biases and stereotypes in training data that are reflected in the LM outputs are causing social problems. In this paper, inspired by the task arithmetic,…
Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by systematic biases. We develop a Bayesian framework to disentangle and quantify three such biases: (i)…
Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models often inherit deep-rooted social biases from their training…
Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…
The Large Language Model Bias Index (LLMBI) is a pioneering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4. We recognise the increasing prevalence and impact of LLMs across diverse…
The advent of transformer-based architectures and large language models (LLMs) have significantly advanced the performance of natural language processing (NLP) models. Since these LLMs are trained on huge corpuses of data from the web and…
The rapid advancement of large language models (LLMs) has enabled natural language processing capabilities similar to those of humans, and LLMs are being widely utilized across various societal domains such as education and healthcare.…
Large Language Models (LLMs) routinely infer users demographic traits from phrasing alone, which can result in biased responses, even when no explicit demographic information is provided. The role of disability cues in shaping these…
Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied. However, the majority of existing methods focus on measuring the model's…
A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…
Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…
This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. Drawing inspiration from seminal works in psycholinguistics, particularly the study of gender's influence on language perception, we…
The training of large language models (LLMs) on extensive, unfiltered corpora sourced from the internet is a common and advantageous practice. Consequently, LLMs have learned and inadvertently reproduced various types of biases, including…