bias-injection

Tag

Cards List
#bias-injection

Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies

arXiv cs.CL ↗ · 4d ago Cached

The paper introduces a controlled bias injection framework for LLM-based multi-agent systems, evaluating how network topologies and injection positions affect the propagation of biased information across five topologies using Qwen and Gemma models, and proposes decision divergence metrics for topology-aware fairness auditing.

0 favorites 0 likes
#bias-injection

Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering

Hugging Face Daily Papers ↗ · 2026-10-05 Cached

The paper demonstrates a targeted bias injection attack on frozen diffusion language models (dLLMs) using a proportional-integral closed-loop controller that adapts steering strength during denoising, strongly increasing biased answers on benchmarks like BBQ and SocialStigmaQA, and argues bias audits must examine the serving stack rather than just the frozen model.

0 favorites 0 likes
← Back to home

Submit Feedback