Inference-Time Steering Improves Cross-Lingual Factual Consistency in LLMs
A new preprint investigates cross-lingual factual inconsistency in large language models (LLMs), where answers shift depending on the prompt language. The researchers evaluate four inference-time interventions on Gemma 3 12B Instruct, including persona prompting, internal representation manipulation, and weight modification. They find that persona prompting—a simple contextual intervention—most effectively balances efficacy, safety, and generalization across languages, outperforming more invasive methods.
Why it matters: This work highlights a practical approach to improving factual consistency in multilingual LLMs, suggesting that simple prompt-based methods can be more robust and transferable than complex interventions.
Full story at: arXiv Computation and Language ↗