Analyzing and mitigating cultural hallucinations of commercial language models in turkish

Y Boztemir, N Çalışkan - Authorea Preprints, 2024 - techrxiv.org
In an era where artificial intelligence is increasingly interfacing with diverse cultural contexts,
the ability of language models to accurately represent and adapt to these contexts is of …

Bigbench: A unified benchmark for social bias in text-to-image generative models based on multi-modal llm

H Luo, H Huang, Z Deng, X Liu, R Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability
to generate high-quality images, which also raises concerns about the social biases in their …

VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary

H Luo, Z Deng, H Huang, X Liu, R Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
With the rapid development of Text-to-Image (T2I) models, biases in human image
generation against demographic social groups become a significant concern, impacting …

Improving Geo-Diversity of Generated Images with Contextualized Vendi Score Guidance

R Askari Hemmat, M Hall, A Sun, C Ross… - … on Computer Vision, 2024 - Springer
With the growing popularity of text-to-image generative models, there has been increasing
focus on understanding their risks and biases. Recent work has found that state-of-the-art …

GEIC: Universal and Multilingual Named Entity Recognition with Large Language Models

H Luo, Y **, X Liu, T Shang, R Chen, Z Liu - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs) have supplanted traditional methods in numerous natural
language processing tasks. Nonetheless, in Named Entity Recognition (NER), existing LLM …

RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models

Z Kou, S Pei, M Jiang, X Zhang - Proceedings of the 2024 …, 2024 - aclanthology.org
Text-to-image prompt refinement (T2I-Refine) aims to rephrase or extend an input prompt
with more descriptive details that can be leveraged to generate images with higher quality …

FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models

H Luo, Z Deng, R Chen, Z Liu - arxiv preprint arxiv:2405.17814, 2024 - arxiv.org
The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have
raised concerns about the biases in their outputs, but existing research lacks a holistic …

Thorns and Algorithms: Navigating Generative AI Challenges Inspired by Giraffes and Acacias

W Hussain - arxiv preprint arxiv:2407.11360, 2024 - arxiv.org
The interplay between humans and Generative AI (Gen AI) draws an insightful parallel with
the dynamic relationship between giraffes and acacias on the African Savannah. Just as …

Severity Controlled Text-to-Image Generative Model Bias Manipulation

J Vice, N Akhtar, R Hartley, A Mian - arxiv preprint arxiv:2404.02530, 2024 - arxiv.org
Text-to-image (T2I) generative models are gaining wide popularity, especially in public
domains. However, their intrinsic bias and potential malicious manipulations remain under …

An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts

DE Rzig, DJ Paul, K Pister, J Henkel… - arxiv preprint arxiv …, 2025 - arxiv.org
The tidal wave of advancements in Large Language Models (LLMs) has led to their swift
integration into application-level logic. Many software systems now use prompts to interact …