conftrace_

bias mitigation

500 papers

Explore in graph

Co-occurring keywords

large language model (13587) gender bia (435) language model (4599) social bia (210) text classification (6793) algorithmic fairness (284) causal inference (1630) spurious correlation (279) bias detection (419) representation learning (6206)

Papers

Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification EMNLP 2025
REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting EMNLP 2025
Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach COLING 2025
Mitigating Bias in Machine Learning: A Comprehensive Review and Novel Approaches AAAI 2025
Power(ful) Associations: Rethinking “Stereotype” for NLP ACL 2025
Privacy Preserving Data Selection for Bias Mitigation in Speech Models ACL 2025
Joint Vision-Language Social Bias Removal for CLIP CVPR 2025
Ensuring Reliable and Transparent Algorithmic Fairness Through Optimal Transport and Uncertainty Quantification IJCAI 2025
NLP for Counterspeech against Hate and Misinformation (CSHAM) ACL 2025
The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing ACL 2025
Towards Reward Fairness in RLHF: From a Resource Allocation Perspective ACL 2025
WEFE: A Python Library for Measuring and Mitigating Bias in Word Embeddings JMLR 2025
LLM Bias Detection and Mitigation through the Lens of Desired Distributions EMNLP 2025
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs NAACL 2025
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings COLING 2025
Option Symbol Matters: Investigating and Mitigating Multiple-Choice Option Symbol Bias of Large Language Models NAACL 2025
The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models EMNLP 2025
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making? NAACL 2025
CURE: Controlled Unlearning for Robust Embeddings — Mitigating Conceptual Shortcuts in Pre-Trained Language Models EMNLP 2025
Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation CVPR 2025
Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models ACL 2025
Debiasing Online Preference Learning via Preference Feature Preservation ACL 2025
Revisiting the Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems COLING 2024
Aequitas Flow: Streamlining Fair ML Experimentation JMLR 2024
PreciseDebias: An Automatic Prompt Engineering Approach for Generative AI To Mitigate Image Demographic Biases WACV 2024