Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect
Researchers introduce Introspection Fine-Tuning (IFT), a method for training small language models to detect and report perturbations in their own internal activations. Applying IFT to Llama-1B increases its sentence-localization accuracy from 9.6% to 60.6%, and the improvement generalizes to held-out tasks, indicating that introspective ability can be trained rather than being solely dependent on model scale.
Why it matters: This work shows that self-monitoring and introspective capabilities can be instilled in small language models, advancing prospects for AI transparency and alignment.
Full story at: arXiv Computation and Language ↗