Latent space bias directions in LLMs capture confidence, not fairness

arXiv:2610.08559 · cs.CL, cs.AI, cs.LG · Submitted 2026-10-06 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-10-06

Updated: 2026-10-06

Terminology

• Latent Space — 1× in this paper · explained in 7 episodes

Sources

• The Falcon Series of Open Language Models
• Debiasing Vision-Language Models via Biased Prompts
• The Llama 3 Herd of Models
• A Survey on Fairness in Large Language Models
• Ministral 3
• Investigating Bias Representations in Llama 2 Chat via Activation Steering
• Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
• Qwen3 Technical Report
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering