#debiasing News & Analysis

4 articles tagged with #debiasing. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · Apr 136/10

🧠

Mitigating Extrinsic Gender Bias for Bangla Classification Tasks

Researchers have developed RandSymKL, a debiasing technique for Bangla language models that mitigates gender bias in classification tasks like sentiment analysis and hate speech detection. The study introduces four manually annotated benchmark datasets with gender-perturbation testing and demonstrates that the approach effectively reduces bias while maintaining competitive accuracy compared to existing methods.

AINeutralarXiv – CS AI · Mar 166/10

🧠

Do LLMs have a Gender (Entropy) Bias?

Researchers discovered that large language models exhibit gender bias at the individual question level, creating different amounts of information for men versus women despite appearing unbiased at category levels. A new benchmark dataset called RealWorldQuestioning was developed, and a simple prompt-based debiasing approach was shown to improve response quality in 78% of cases.

🏢 Hugging Face🧠 ChatGPT

AINeutralarXiv – CS AI · Mar 116/10

🧠

Debiasing International Attitudes: LLM Agents for Simulating US-China Perception Changes

Researchers developed an LLM-agent framework to model how media influences US-China attitudes from 2005-2025, testing three debiasing mechanisms to reduce AI model prejudices. The study found that devil's advocate agents were most effective at producing human-like opinion formation, while revealing geographic biases tied to AI models' origins.

🧠 GPT-4

AINeutralarXiv – CS AI · Mar 175/10

🧠

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation

Researchers propose CAP-TTA, a test-time adaptation framework that helps debiased large language models better handle unfamiliar toxic prompts that cause distribution shifts. The method uses context-aware LoRA updates triggered by bias-risk thresholds to reduce toxic outputs while maintaining narrative fluency and reducing computational latency.