Location

Hilton Waikoloa Village, Hawaii

Event Website

https://hicss.hawaii.edu/

Start Date

7-1-2025 12:00 AM

End Date

10-1-2025 12:00 AM

Description

Language models often struggle to accurately evaluate and mitigate biases across different domains. This limitation stems from their reliance on static, context-agnostic evaluation methods that fail to capture the nuanced, context-dependent nature of biases. Our research introduces a multi-agent framework utilizing causal abductive reasoning to address these shortcomings. The approach collaborates agents for contextual coherence, stereotype detection, semantic evaluation, and causal plausibility, which refine their assessments through an adaptive multi-round negotiation and confidence adjustment mechanism. Experimental results reveal that our framework significantly outperforms existing models in detecting and mitigating biases.

Share

COinS
 
Jan 7th, 12:00 AM Jan 10th, 12:00 AM

Minimal Agents, Maximum Bias Insight

Hilton Waikoloa Village, Hawaii

Language models often struggle to accurately evaluate and mitigate biases across different domains. This limitation stems from their reliance on static, context-agnostic evaluation methods that fail to capture the nuanced, context-dependent nature of biases. Our research introduces a multi-agent framework utilizing causal abductive reasoning to address these shortcomings. The approach collaborates agents for contextual coherence, stereotype detection, semantic evaluation, and causal plausibility, which refine their assessments through an adaptive multi-round negotiation and confidence adjustment mechanism. Experimental results reveal that our framework significantly outperforms existing models in detecting and mitigating biases.

https://aisel.aisnet.org/hicss-58/sj/discrimination/3