Activation steering with FLORES-derived language vectors produces modest, layer-sensitive and language-dependent gains on cultural awareness tasks, with some settings degrading performance and strong interaction with prompt design.
Llama 2: Open foundation and fine-tuned chat models , url =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
Activation steering with FLORES-derived language vectors produces modest, layer-sensitive and language-dependent gains on cultural awareness tasks, with some settings degrading performance and strong interaction with prompt design.
- InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees