conftrace_

bias amplification

26 papers

Explore in graph

Co-occurring keywords

gender bia (435) large language model (13587) social bia (210) protected attribute (24) dataset bia (149) image captioning (731) fairness evaluation (118) political bia (57) multi-agent system (1819) model collapse (23)

Papers

Position: Biomedical NLP Demands Specialization, Not Generalization EACL 2026
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions WACV 2026
How I Met Your Bias: Investigating Bias Amplification in Diffusion Models WACV 2026
HEV Generative Sandbox: A Framework for Assessing Domain-Specific Social Risks Through Human-LLM Simulation AAAI 2026
An Empirical Study of Group Conformity in Multi-Agent Systems ACL 2025
Bias Amplification: Large Language Models as Increasingly Biased Media IJCNLP 2025
Bias Amplification: Large Language Models as Increasingly Biased Media AACL 2025
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective NIPS 2024
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making NIPS 2024
The Trade-off between Performance, Efficiency, and Fairness in Adapter Modules for Text Classification NAACL 2024
Would Deep Generative Models Amplify Bias in Future Models? CVPR 2024
“Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models EMNLP 2024
ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment AAAI 2024
The Bias Amplification Paradox in Text-to-Image Generation NAACL 2024
The Rise of AI-Generated Content in Wikipedia EMNLP 2024
Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models EMNLP 2023
Men Also Do Laundry: Multi-Attribute Bias Amplification ICML 2023
Revisiting the Importance of Amplifying Bias for Debiasing AAAI 2023
Data Feedback Loops: Model-driven Amplification of Dataset Biases ICML 2023
Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases ACL 2023
What Do Compressed Multilingual Machine Translation Models Forget? EMNLP 2022
Quantifying Societal Bias Amplification in Image Captioning CVPR 2022
Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour IJCNLP 2022
Directional Bias Amplification ICML 2021
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization ACL 2020